[{"date_updated":"2022-01-06T06:51:07Z","author":[{"full_name":"Beyerlein, Peter","last_name":"Beyerlein","first_name":"Peter"},{"last_name":"Aubert","first_name":"Xavier L.","full_name":"Aubert, Xavier L."},{"last_name":"Haeb-Umbach","first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","id":"242"},{"full_name":"Harris, Matthew J.","last_name":"Harris","first_name":"Matthew J."},{"full_name":"Klakow, Dietrich","first_name":"Dietrich","last_name":"Klakow"},{"full_name":"Wendemuth, Andreas","last_name":"Wendemuth","first_name":"Andreas"},{"first_name":"Sirko","last_name":"Molau","full_name":"Molau, Sirko"},{"first_name":"Michael","last_name":"Pitz","full_name":"Pitz, Michael"},{"full_name":"Sixtus, Achim","first_name":"Achim","last_name":"Sixtus"}],"title":"The Philips/RWTH System for Transcription of Broadcast News","year":"1999","status":"public","user_id":"44006","_id":"11729","language":[{"iso":"eng"}],"main_file_link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/1999/Workshop_Washington_1999_Haeb_paper.pdf","open_access":"1"}],"abstract":[{"lang":"eng","text":"This paper contains a description of the Philips/RWTH 1998 HUB4 system which has been build in a joint e ort of Philips Research Laboratories Aachen and Aachen University of Technology. We will focus our discussion on recent improvements compared to the original 1997 HUB4 system and evaluate them on the HUB4'97 evaluation data. The paper will deal with 1. a rough system overview including feature extraction, acoustic training, audio stream segmentation, and decoding 2. log-linear interpolation of distance-language models, 3. and the integration of various acoustic and language models via Discriminative Model Combination (DMC). The performance of the described system is 23% (relative) better than the performance of the 1997 Philips HUB4 system. A word error rate of 17.9% was achieved on the 1997 HUB4 evaluation set, compared to 23.5% using the original 1997 system."}],"citation":{"mla":"Beyerlein, Peter, et al. “The Philips/RWTH System for Transcription of Broadcast News.” <i>Broadcast News Transcription and Understanding Workshop, Washington</i>, 1999.","ama":"Beyerlein P, Aubert XL, Haeb-Umbach R, et al. The Philips/RWTH System for Transcription of Broadcast News. In: <i>Broadcast News Transcription and Understanding Workshop, Washington</i>. ; 1999.","bibtex":"@inproceedings{Beyerlein_Aubert_Haeb-Umbach_Harris_Klakow_Wendemuth_Molau_Pitz_Sixtus_1999, title={The Philips/RWTH System for Transcription of Broadcast News}, booktitle={Broadcast News Transcription and Understanding Workshop, Washington}, author={Beyerlein, Peter and Aubert, Xavier L. and Haeb-Umbach, Reinhold and Harris, Matthew J. and Klakow, Dietrich and Wendemuth, Andreas and Molau, Sirko and Pitz, Michael and Sixtus, Achim}, year={1999} }","apa":"Beyerlein, P., Aubert, X. L., Haeb-Umbach, R., Harris, M. J., Klakow, D., Wendemuth, A., … Sixtus, A. (1999). The Philips/RWTH System for Transcription of Broadcast News. In <i>Broadcast News Transcription and Understanding Workshop, Washington</i>.","ieee":"P. Beyerlein <i>et al.</i>, “The Philips/RWTH System for Transcription of Broadcast News,” in <i>Broadcast News Transcription and Understanding Workshop, Washington</i>, 1999.","short":"P. Beyerlein, X.L. Aubert, R. Haeb-Umbach, M.J. Harris, D. Klakow, A. Wendemuth, S. Molau, M. Pitz, A. Sixtus, in: Broadcast News Transcription and Understanding Workshop, Washington, 1999.","chicago":"Beyerlein, Peter, Xavier L. Aubert, Reinhold Haeb-Umbach, Matthew J. Harris, Dietrich Klakow, Andreas Wendemuth, Sirko Molau, Michael Pitz, and Achim Sixtus. “The Philips/RWTH System for Transcription of Broadcast News.” In <i>Broadcast News Transcription and Understanding Workshop, Washington</i>, 1999."},"publication":"Broadcast News Transcription and Understanding Workshop, Washington","department":[{"_id":"54"}],"oa":"1","type":"conference","date_created":"2019-07-12T05:27:08Z"},{"citation":{"apa":"Haeb-Umbach, R. (1999). Investigations on inter-speaker variability in the feature space. In <i>ICASSP99 Phoenix, AZ</i>.","mla":"Haeb-Umbach, Reinhold. “Investigations on Inter-Speaker Variability in the Feature Space.” <i>ICASSP99 Phoenix, AZ</i>, 1999.","ieee":"R. Haeb-Umbach, “Investigations on inter-speaker variability in the feature space,” in <i>ICASSP99 Phoenix, AZ</i>, 1999.","short":"R. Haeb-Umbach, in: ICASSP99 Phoenix, AZ, 1999.","ama":"Haeb-Umbach R. Investigations on inter-speaker variability in the feature space. In: <i>ICASSP99 Phoenix, AZ</i>. ; 1999.","chicago":"Haeb-Umbach, Reinhold. “Investigations on Inter-Speaker Variability in the Feature Space.” In <i>ICASSP99 Phoenix, AZ</i>, 1999.","bibtex":"@inproceedings{Haeb-Umbach_1999, title={Investigations on inter-speaker variability in the feature space}, booktitle={ICASSP99 Phoenix, AZ}, author={Haeb-Umbach, Reinhold}, year={1999} }"},"publication":"ICASSP99 Phoenix, AZ","abstract":[{"text":"We apply Fisher variate analysis to measure the effectiveness of speaker normalization techniques. A trace criterion, which measures the ratio of the variations due to different phonemes compared to variations due to different speakers, serves as a first assessment of a feature set without the need for recognition experiments. By using this measure and by recognition experiments we demonstrate that cepstral mean normalization also has a speaker normalization effect, in addition to the well-known channel normalization effect. Similarly vocal tract normalization (VTN) is shown to remove inter-speaker variability. For VTN we show that normalization on a per sentence basis performs better than normalization on a per speaker basis. Recognition results are given on Wall Street Journal and Hub-4 databases","lang":"eng"}],"date_created":"2019-07-12T05:28:07Z","oa":"1","department":[{"_id":"54"}],"type":"conference","author":[{"full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242"}],"title":"Investigations on inter-speaker variability in the feature space","year":"1999","status":"public","date_updated":"2022-01-06T06:51:08Z","_id":"11780","language":[{"iso":"eng"}],"main_file_link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/1999/ICASSP_1999_Haeb_paper.pdf","open_access":"1"}],"user_id":"44006"},{"abstract":[{"text":"We examined variants of MFCC and PLP cepstral parameterisations in the context of large vocabulary continuous speech recognition under different acous-tical environmental conditions: Compared to MFCC, mel-frequency PLP uses a cubic root intensity-to-loudness law, and an LPC analysis is applied to the mel-warped spectrum. In LPC-smoothed MFCC, the only difference to MFCC is the additional LPC smoothing of the warped spectrum. While neither technique was able to significantly outperform the MFCC parameterisation in our setup which includes an LDA feature transformation, feature set combination via DMC at the acoustic likelihood level and via ROVER at the recognized word level delivered small but consistent improvements.","lang":"eng"}],"citation":{"bibtex":"@inproceedings{Haeb-Umbach_Loog_1999, title={An Investigation of Cepstral Parameterisations for Large Vocabulary Speech Recognition}, booktitle={Eurospeech}, author={Haeb-Umbach, Reinhold and Loog, Marco}, year={1999} }","ama":"Haeb-Umbach R, Loog M. An Investigation of Cepstral Parameterisations for Large Vocabulary Speech Recognition. In: <i>Eurospeech</i>. ; 1999.","mla":"Haeb-Umbach, Reinhold, and Marco Loog. “An Investigation of Cepstral Parameterisations for Large Vocabulary Speech Recognition.” <i>Eurospeech</i>, 1999.","chicago":"Haeb-Umbach, Reinhold, and Marco Loog. “An Investigation of Cepstral Parameterisations for Large Vocabulary Speech Recognition.” In <i>Eurospeech</i>, 1999.","short":"R. Haeb-Umbach, M. Loog, in: Eurospeech, 1999.","ieee":"R. Haeb-Umbach and M. Loog, “An Investigation of Cepstral Parameterisations for Large Vocabulary Speech Recognition,” in <i>Eurospeech</i>, 1999.","apa":"Haeb-Umbach, R., &#38; Loog, M. (1999). An Investigation of Cepstral Parameterisations for Large Vocabulary Speech Recognition. In <i>Eurospeech</i>."},"publication":"Eurospeech","department":[{"_id":"54"}],"oa":"1","type":"conference","date_created":"2019-07-12T05:28:19Z","date_updated":"2022-01-06T06:51:08Z","author":[{"last_name":"Haeb-Umbach","first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","id":"242"},{"full_name":"Loog, Marco","last_name":"Loog","first_name":"Marco"}],"status":"public","title":"An Investigation of Cepstral Parameterisations for Large Vocabulary Speech Recognition","year":"1999","user_id":"44006","language":[{"iso":"eng"}],"_id":"11791","main_file_link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/1999/Eurospeech_1999_Haeb_paper.pdf","open_access":"1"}]},{"date_created":"2019-07-12T05:28:36Z","type":"conference","oa":"1","department":[{"_id":"54"}],"publication":"Eurospeech","citation":{"ama":"Harris MJ, Aubert XL, Haeb-Umbach R, Beyerlein P. A study of broadcast news audio stream segmentation and segment clustering. In: <i>Eurospeech</i>. ; 1999.","bibtex":"@inproceedings{Harris_Aubert_Haeb-Umbach_Beyerlein_1999, title={A study of broadcast news audio stream segmentation and segment clustering}, booktitle={Eurospeech}, author={Harris, Matthew J. and Aubert, Xavier L. and Haeb-Umbach, Reinhold and Beyerlein, Peter}, year={1999} }","mla":"Harris, Matthew J., et al. “A Study of Broadcast News Audio Stream Segmentation and Segment Clustering.” <i>Eurospeech</i>, 1999.","chicago":"Harris, Matthew J., Xavier L. Aubert, Reinhold Haeb-Umbach, and Peter Beyerlein. “A Study of Broadcast News Audio Stream Segmentation and Segment Clustering.” In <i>Eurospeech</i>, 1999.","short":"M.J. Harris, X.L. Aubert, R. Haeb-Umbach, P. Beyerlein, in: Eurospeech, 1999.","apa":"Harris, M. J., Aubert, X. L., Haeb-Umbach, R., &#38; Beyerlein, P. (1999). A study of broadcast news audio stream segmentation and segment clustering. In <i>Eurospeech</i>.","ieee":"M. J. Harris, X. L. Aubert, R. Haeb-Umbach, and P. Beyerlein, “A study of broadcast news audio stream segmentation and segment clustering,” in <i>Eurospeech</i>, 1999."},"abstract":[{"text":"In transcription of broadcast news, dividing the signal into homogeneous segments, and clustering together similar segments is important. Decoding a complete broadcast news program in one chunk is technically di cult. Also, through creation of homogeneous clusters of segments, improvement from adaptation can be increased. Two systems of segmentation and clustering are compared. The best system used the BIC algorithm to produce long, homogeneous segments, and a nearest neighbour bottom-up agglomerative clustering algorithm to produce homogeneous clusters. Adaptation brought a word error rate (WER) improvement from 23:4% to 21:0% using the automatic segmentation and clustering, compared to an improvement from 21:8% to 20:0% using a handmade \\correct\" segmentation and clustering.","lang":"eng"}],"main_file_link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/1999/Eurospeech_1_1999_Haeb_paper.pdf","open_access":"1"}],"language":[{"iso":"eng"}],"_id":"11805","user_id":"44006","year":"1999","status":"public","title":"A study of broadcast news audio stream segmentation and segment clustering","author":[{"first_name":"Matthew J.","last_name":"Harris","full_name":"Harris, Matthew J."},{"first_name":"Xavier L.","last_name":"Aubert","full_name":"Aubert, Xavier L."},{"full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242"},{"first_name":"Peter","last_name":"Beyerlein","full_name":"Beyerlein, Peter"}],"date_updated":"2022-01-06T06:51:09Z"},{"date_created":"2019-07-12T05:27:09Z","type":"conference","oa":"1","department":[{"_id":"54"}],"publication":"DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne","citation":{"bibtex":"@inproceedings{Beyerlein_Aubert_Haeb-Umbach_Klakow_Ullrich_Wendemuth_Wilcox_1998, title={Automatic Transcription of English Broadcast News}, booktitle={DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne}, author={Beyerlein, Peter and Aubert, Xavier L. and Haeb-Umbach, Reinhold and Klakow, Dietrich and Ullrich, Meinhard and Wendemuth, Andreas and Wilcox, Patricia}, year={1998} }","chicago":"Beyerlein, Peter, Xavier L. Aubert, Reinhold Haeb-Umbach, Dietrich Klakow, Meinhard Ullrich, Andreas Wendemuth, and Patricia Wilcox. “Automatic Transcription of English Broadcast News.” In <i>DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne</i>, 1998.","ama":"Beyerlein P, Aubert XL, Haeb-Umbach R, et al. Automatic Transcription of English Broadcast News. In: <i>DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne</i>. ; 1998.","short":"P. Beyerlein, X.L. Aubert, R. Haeb-Umbach, D. Klakow, M. Ullrich, A. Wendemuth, P. Wilcox, in: DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne, 1998.","ieee":"P. Beyerlein <i>et al.</i>, “Automatic Transcription of English Broadcast News,” in <i>DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne</i>, 1998.","apa":"Beyerlein, P., Aubert, X. L., Haeb-Umbach, R., Klakow, D., Ullrich, M., Wendemuth, A., &#38; Wilcox, P. (1998). Automatic Transcription of English Broadcast News. In <i>DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne</i>.","mla":"Beyerlein, Peter, et al. “Automatic Transcription of English Broadcast News.” <i>DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne</i>, 1998."},"abstract":[{"text":"In this paper the Philips Broadcast News transcription system is described. The Broadcast News task aims at the recognition of \"found\" speech in radio and television broadcasts without any additional side information (e.g. speaking style, background conditions). The system was derived from the Philips continuous mixture density crossword HMM system, using MFCC features and Laplacian densities. A segmentation was performed to obtain sentence-like partitions of the broadcasts. Using data-driven clustering, the obtained segments were grouped into clusters with similar acoustic conditions for adaptation purposes. Gender independent word-internal and crossword triphone models were trained on 70 hours of the HUB4 training data. No focus condition specific training was applied. Channel and speaker normalization was done by mean and variance normalization as well as VTN and MLLR. The transcription was produced by an adaptive multiple pass decoder starting with phrase-bigram decoding using word-internal triphones and finishing with a phrase-trigram decoding using MLLR-adapted crossword models.","lang":"eng"}],"main_file_link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/1998/Workshop_Lansdowne_1998_Haeb_paper.pdf","open_access":"1"}],"language":[{"iso":"eng"}],"_id":"11730","user_id":"44006","title":"Automatic Transcription of English Broadcast News","status":"public","year":"1998","author":[{"full_name":"Beyerlein, Peter","first_name":"Peter","last_name":"Beyerlein"},{"last_name":"Aubert","first_name":"Xavier L.","full_name":"Aubert, Xavier L."},{"first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242"},{"first_name":"Dietrich","last_name":"Klakow","full_name":"Klakow, Dietrich"},{"first_name":"Meinhard","last_name":"Ullrich","full_name":"Ullrich, Meinhard"},{"full_name":"Wendemuth, Andreas","first_name":"Andreas","last_name":"Wendemuth"},{"first_name":"Patricia","last_name":"Wilcox","full_name":"Wilcox, Patricia"}],"date_updated":"2022-01-06T06:51:08Z"},{"date_created":"2019-07-12T05:28:11Z","type":"conference","oa":"1","department":[{"_id":"54"}],"publication":"DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne","citation":{"apa":"Haeb-Umbach, R., Aubert, X. L., Beyerlein, P., Klakow, D., Ullrich, M., Wendemuth, A., &#38; Wilcox, P. (1998). Acoustic Modeling in the Philips Hub-4 Continuous-Speech Recognition System. In <i>DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne</i>.","ieee":"R. Haeb-Umbach <i>et al.</i>, “Acoustic Modeling in the Philips Hub-4 Continuous-Speech Recognition System,” in <i>DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne</i>, 1998.","short":"R. Haeb-Umbach, X.L. Aubert, P. Beyerlein, D. Klakow, M. Ullrich, A. Wendemuth, P. Wilcox, in: DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne, 1998.","chicago":"Haeb-Umbach, Reinhold, Xavier L. Aubert, Peter Beyerlein, Dietrich Klakow, Meinhard Ullrich, Andreas Wendemuth, and Patricia Wilcox. “Acoustic Modeling in the Philips Hub-4 Continuous-Speech Recognition System.” In <i>DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne</i>, 1998.","mla":"Haeb-Umbach, Reinhold, et al. “Acoustic Modeling in the Philips Hub-4 Continuous-Speech Recognition System.” <i>DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne</i>, 1998.","ama":"Haeb-Umbach R, Aubert XL, Beyerlein P, et al. Acoustic Modeling in the Philips Hub-4 Continuous-Speech Recognition System. In: <i>DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne</i>. ; 1998.","bibtex":"@inproceedings{Haeb-Umbach_Aubert_Beyerlein_Klakow_Ullrich_Wendemuth_Wilcox_1998, title={Acoustic Modeling in the Philips Hub-4 Continuous-Speech Recognition System}, booktitle={DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne}, author={Haeb-Umbach, Reinhold and Aubert, Xavier L. and Beyerlein, Peter and Klakow, Dietrich and Ullrich, Meinhard and Wendemuth, Andreas and Wilcox, Patricia}, year={1998} }"},"abstract":[{"text":"In this paper we describe some characteristics of the acoustic modeling used in the Philips continuous-speech recognition system for the DARPA Hub-4 1997 evaluation, which are related to robustness issues. We aimed at a conceptually simple system: We trained two model sets on 70 hours of the Hub-4 training data, one for within-word and one for cross-word decoding. These model sets were used for both genders and all environmental conditions. In order to be able to do so, channel normalization (mean, variance normalization) and speaker normalization (vocal tract length normalization, realized by an appropriate shift of the center frequencies of the mel filter bank) have been applied, as well as adaptation techniques. MLLR-based unsupervised batch adaptation on clusters of segments was conducted both after a first within-word decoding and a cross-word decoding pass. The training strategy and the effects of the various normalization and adaptation techniques will be discussed in the paper.","lang":"eng"}],"main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/1998/Workshop_Landsdowne_1998_Haeb2_paper.pdf"}],"language":[{"iso":"eng"}],"_id":"11784","user_id":"44006","status":"public","year":"1998","title":"Acoustic Modeling in the Philips Hub-4 Continuous-Speech Recognition System","author":[{"id":"242","full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold","last_name":"Haeb-Umbach"},{"first_name":"Xavier L.","last_name":"Aubert","full_name":"Aubert, Xavier L."},{"last_name":"Beyerlein","first_name":"Peter","full_name":"Beyerlein, Peter"},{"full_name":"Klakow, Dietrich","last_name":"Klakow","first_name":"Dietrich"},{"full_name":"Ullrich, Meinhard","last_name":"Ullrich","first_name":"Meinhard"},{"first_name":"Andreas","last_name":"Wendemuth","full_name":"Wendemuth, Andreas"},{"full_name":"Wilcox, Patricia","last_name":"Wilcox","first_name":"Patricia"}],"date_updated":"2022-01-06T06:51:08Z"},{"date_updated":"2022-01-06T06:51:11Z","status":"public","title":"Language-Model Investigations related to Broadcast News","year":"1998","author":[{"last_name":"Klakow","first_name":"Dietrich","full_name":"Klakow, Dietrich"},{"full_name":"Aubert, Xavier L.","first_name":"Xavier L.","last_name":"Aubert"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold","last_name":"Haeb-Umbach"},{"last_name":"Beyerlein","first_name":"Peter","full_name":"Beyerlein, Peter"},{"full_name":"Ullrich, Meinhard","last_name":"Ullrich","first_name":"Meinhard"},{"full_name":"Wendemuth, Andreas","last_name":"Wendemuth","first_name":"Andreas"},{"first_name":"Patricia","last_name":"Wilcox","full_name":"Wilcox, Patricia"}],"user_id":"44006","main_file_link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/1998/Workshop_Lansdowne_1998_Haeb1_paper.pdf","open_access":"1"}],"language":[{"iso":"eng"}],"_id":"11842","abstract":[{"lang":"eng","text":"In this paper we present some experiments that have been performed while developing language models for the PHILIPS Broadcast News system. Three main issues will be discussed: construction of phrases, adaptation of remote corpora to this task, and the combination of the different models. Also, perplexities on the 1997 evaluation data are reported."}],"publication":"DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne","citation":{"mla":"Klakow, Dietrich, et al. “Language-Model Investigations Related to Broadcast News.” <i>DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne</i>, 1998.","bibtex":"@inproceedings{Klakow_Aubert_Haeb-Umbach_Beyerlein_Ullrich_Wendemuth_Wilcox_1998, title={Language-Model Investigations related to Broadcast News}, booktitle={DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne}, author={Klakow, Dietrich and Aubert, Xavier L. and Haeb-Umbach, Reinhold and Beyerlein, Peter and Ullrich, Meinhard and Wendemuth, Andreas and Wilcox, Patricia}, year={1998} }","ama":"Klakow D, Aubert XL, Haeb-Umbach R, et al. Language-Model Investigations related to Broadcast News. In: <i>DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne</i>. ; 1998.","ieee":"D. Klakow <i>et al.</i>, “Language-Model Investigations related to Broadcast News,” in <i>DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne</i>, 1998.","apa":"Klakow, D., Aubert, X. L., Haeb-Umbach, R., Beyerlein, P., Ullrich, M., Wendemuth, A., &#38; Wilcox, P. (1998). Language-Model Investigations related to Broadcast News. In <i>DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne</i>.","short":"D. Klakow, X.L. Aubert, R. Haeb-Umbach, P. Beyerlein, M. Ullrich, A. Wendemuth, P. Wilcox, in: DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne, 1998.","chicago":"Klakow, Dietrich, Xavier L. Aubert, Reinhold Haeb-Umbach, Peter Beyerlein, Meinhard Ullrich, Andreas Wendemuth, and Patricia Wilcox. “Language-Model Investigations Related to Broadcast News.” In <i>DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne</i>, 1998."},"type":"conference","oa":"1","department":[{"_id":"54"}],"date_created":"2019-07-12T05:29:19Z"},{"status":"public","year":"1998","title":"A Study on Speaker Normalization Using Vocal Tract Normalization and Speaker Adaptive Training","author":[{"full_name":"Welling, L.","first_name":"L.","last_name":"Welling"},{"last_name":"Haeb-Umbach","first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","id":"242"},{"last_name":"Aubert","first_name":"X.","full_name":"Aubert, X."},{"last_name":"Haberland","first_name":"N.","full_name":"Haberland, N."}],"date_updated":"2022-01-06T06:51:12Z","main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/1998/ICASSP_1998_Haeb_paper.pdf"}],"_id":"11936","language":[{"iso":"eng"}],"user_id":"44006","publication":"ICASSP 1998, Seattle","citation":{"apa":"Welling, L., Haeb-Umbach, R., Aubert, X., &#38; Haberland, N. (1998). A Study on Speaker Normalization Using Vocal Tract Normalization and Speaker Adaptive Training. In <i>ICASSP 1998, Seattle</i>.","ieee":"L. Welling, R. Haeb-Umbach, X. Aubert, and N. Haberland, “A Study on Speaker Normalization Using Vocal Tract Normalization and Speaker Adaptive Training,” in <i>ICASSP 1998, Seattle</i>, 1998.","short":"L. Welling, R. Haeb-Umbach, X. Aubert, N. Haberland, in: ICASSP 1998, Seattle, 1998.","chicago":"Welling, L., Reinhold Haeb-Umbach, X. Aubert, and N. Haberland. “A Study on Speaker Normalization Using Vocal Tract Normalization and Speaker Adaptive Training.” In <i>ICASSP 1998, Seattle</i>, 1998.","mla":"Welling, L., et al. “A Study on Speaker Normalization Using Vocal Tract Normalization and Speaker Adaptive Training.” <i>ICASSP 1998, Seattle</i>, 1998.","ama":"Welling L, Haeb-Umbach R, Aubert X, Haberland N. A Study on Speaker Normalization Using Vocal Tract Normalization and Speaker Adaptive Training. In: <i>ICASSP 1998, Seattle</i>. ; 1998.","bibtex":"@inproceedings{Welling_Haeb-Umbach_Aubert_Haberland_1998, title={A Study on Speaker Normalization Using Vocal Tract Normalization and Speaker Adaptive Training}, booktitle={ICASSP 1998, Seattle}, author={Welling, L. and Haeb-Umbach, Reinhold and Aubert, X. and Haberland, N.}, year={1998} }"},"abstract":[{"text":"Although speaker normalization is attempted in very different manners, vocal tract normalization (VTN) and speaker adaptive training (SAT) share many common properties. We show that both lead to more compact representations of the phonetically relevant variations of the training data and that both achieve improved error rate performance only if a complementary normalization or adaptation operation is conducted on the test data. Algorithms for fast test speaker enrollment are presented for both normalization methods: in the framework of SAT, a pre-transformation step is proposed, which alone, i.e. without subsequent unsupervised MLLR adaption, reduces the error rate by almost 10% on the WSJ 5k test sets. For VTN, the use of a Gaussian mixture model makes obsolete a first recognition pass to obtain a preliminary transcription of the test utterance at hardly and loss in performance.","lang":"eng"}],"date_created":"2019-07-12T05:31:07Z","type":"conference","oa":"1","department":[{"_id":"54"}]},{"main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/1997/ICASSP_1997_Haeb1_paper.pdf"}],"language":[{"iso":"eng"}],"_id":"11750","user_id":"44006","year":"1997","title":"Signal Representations for Hidden Markov Model Based On-Line Handwriting Recognition","status":"public","author":[{"full_name":"Dolfing, J.G.A.","last_name":"Dolfing","first_name":"J.G.A."},{"id":"242","first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold"}],"date_updated":"2022-01-06T06:51:08Z","date_created":"2019-07-12T05:27:32Z","type":"conference","oa":"1","department":[{"_id":"54"}],"publication":"ICASSP, Munich","citation":{"chicago":"Dolfing, J.G.A., and Reinhold Haeb-Umbach. “Signal Representations for Hidden Markov Model Based On-Line Handwriting Recognition.” In <i>ICASSP, Munich</i>, 1997.","ama":"Dolfing JGA, Haeb-Umbach R. Signal Representations for Hidden Markov Model Based On-Line Handwriting Recognition. In: <i>ICASSP, Munich</i>. ; 1997.","short":"J.G.A. Dolfing, R. Haeb-Umbach, in: ICASSP, Munich, 1997.","bibtex":"@inproceedings{Dolfing_Haeb-Umbach_1997, title={Signal Representations for Hidden Markov Model Based On-Line Handwriting Recognition}, booktitle={ICASSP, Munich}, author={Dolfing, J.G.A. and Haeb-Umbach, Reinhold}, year={1997} }","mla":"Dolfing, J. G. A., and Reinhold Haeb-Umbach. “Signal Representations for Hidden Markov Model Based On-Line Handwriting Recognition.” <i>ICASSP, Munich</i>, 1997.","apa":"Dolfing, J. G. A., &#38; Haeb-Umbach, R. (1997). Signal Representations for Hidden Markov Model Based On-Line Handwriting Recognition. In <i>ICASSP, Munich</i>.","ieee":"J. G. A. Dolfing and R. Haeb-Umbach, “Signal Representations for Hidden Markov Model Based On-Line Handwriting Recognition,” in <i>ICASSP, Munich</i>, 1997."},"abstract":[{"text":"Addresses the problem of online, writer-independent, unconstrained handwriting recognition. Based on hidden Markov models (HMM), which are successfully employed in speech recognition tasks, we focus on representations which address scalability, recognition performance and compactness. 'Delayed' features are introduced which integrate more global, handwriting specific knowledge into the HMM representation. These features lead to larger error-rate reduction than 'delta' features which are known from speech recognition and even require fewer additional components. Scalability is addressed with a size-independent representation. Compactness is achieved with linear discriminant analysis. The representations are discussed and the results for a mixed-style word recognition task with vocabularies of 200 (up to 99% correct words) and 20000 words (up to 88.8% correct words) are given.","lang":"eng"}]},{"date_created":"2019-07-12T05:27:50Z","type":"journal_article","department":[{"_id":"54"}],"publication":"Speech Communication","citation":{"bibtex":"@article{Gamm_Haeb-Umbach_Langmann_1997, title={The development of a command-based speech interface for a telephone answering machine}, journal={Speech Communication}, author={Gamm, Stephan and Haeb-Umbach, Reinhold and Langmann, Detlev}, year={1997} }","ama":"Gamm S, Haeb-Umbach R, Langmann D. The development of a command-based speech interface for a telephone answering machine. <i>Speech Communication</i>. 1997.","mla":"Gamm, Stephan, et al. “The Development of a Command-Based Speech Interface for a Telephone Answering Machine.” <i>Speech Communication</i>, 1997.","short":"S. Gamm, R. Haeb-Umbach, D. Langmann, Speech Communication (1997).","chicago":"Gamm, Stephan, Reinhold Haeb-Umbach, and Detlev Langmann. “The Development of a Command-Based Speech Interface for a Telephone Answering Machine.” <i>Speech Communication</i>, 1997.","ieee":"S. Gamm, R. Haeb-Umbach, and D. Langmann, “The development of a command-based speech interface for a telephone answering machine,” <i>Speech Communication</i>, 1997.","apa":"Gamm, S., Haeb-Umbach, R., &#38; Langmann, D. (1997). The development of a command-based speech interface for a telephone answering machine. <i>Speech Communication</i>."},"abstract":[{"text":"This paper reports the design of a command-based speech interface for an answering machine or a voice mail system. Automatic speech recognition was integrated in order to facilitate the remote control and the retrieval of voice messages from any telephone in a speech-only dialogue. The design goal was that consumers would perceive the speech interface as a benefit compared with the common touch-tone interface. In this paper we will first describe the speech technology underlying the system. Then it will be shown how, based on this technology, the user interface was designed in a top-down approach. We started with the development of a concept and tested it by means of a Wizard-of-Oz simulation. After refining the concept in parallel design, it was implemented in a high-fidelity prototype. By means of qualitative user testing the design was improved in three iteration steps. The achievement of the design goal was finally verified with user tests in two countries.","lang":"eng"}],"language":[{"iso":"eng"}],"_id":"11766","user_id":"44006","title":"The development of a command-based speech interface for a telephone answering machine","year":"1997","status":"public","author":[{"full_name":"Gamm, Stephan","first_name":"Stephan","last_name":"Gamm"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"},{"last_name":"Langmann","first_name":"Detlev","full_name":"Langmann, Detlev"}],"date_updated":"2022-01-06T06:51:08Z"},{"user_id":"44006","_id":"11781","language":[{"iso":"eng"}],"main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/1997/Eurospeech_1997_Haeb1_paper.pdf"}],"date_updated":"2022-01-06T06:51:08Z","author":[{"id":"242","full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold","last_name":"Haeb-Umbach"}],"status":"public","year":"1997","title":"Robust Speech Recognition for Wireless Networks and Mobile Telephony","oa":"1","department":[{"_id":"54"}],"type":"conference","date_created":"2019-07-12T05:28:08Z","abstract":[{"lang":"eng","text":"The increased popularity of mobile telephony introduces both challenges and opportunitites for automatic speech recognition. ASR offers ways to simplify the use of mobile phones, notably in hands- and eyes-busy situations. However, the acoustic environment can be severely degraded and the wireless network may add additional distortions to the speech signal. This paper gives an overview of the sources of degradation and attempts to robust speech recognition for mobile communications. Emphasis is placed on approaches which are suitable for implementation in mobile terminals. Two example applications are described which illustrate the robustness issues and design considerations typical of low-cost noisy speech recognition: voice-dialling in a GSM phone and hands-free digit recognition in the car."}],"citation":{"apa":"Haeb-Umbach, R. (1997). Robust Speech Recognition for Wireless Networks and Mobile Telephony. In <i>Eurospeech</i>.","ieee":"R. Haeb-Umbach, “Robust Speech Recognition for Wireless Networks and Mobile Telephony,” in <i>Eurospeech</i>, 1997.","chicago":"Haeb-Umbach, Reinhold. “Robust Speech Recognition for Wireless Networks and Mobile Telephony.” In <i>Eurospeech</i>, 1997.","short":"R. Haeb-Umbach, in: Eurospeech, 1997.","mla":"Haeb-Umbach, Reinhold. “Robust Speech Recognition for Wireless Networks and Mobile Telephony.” <i>Eurospeech</i>, 1997.","ama":"Haeb-Umbach R. Robust Speech Recognition for Wireless Networks and Mobile Telephony. In: <i>Eurospeech</i>. ; 1997.","bibtex":"@inproceedings{Haeb-Umbach_1997, title={Robust Speech Recognition for Wireless Networks and Mobile Telephony}, booktitle={Eurospeech}, author={Haeb-Umbach, Reinhold}, year={1997} }"},"publication":"Eurospeech"},{"date_created":"2019-07-12T05:28:52Z","oa":"1","department":[{"_id":"54"}],"type":"conference","citation":{"short":"H. Hoege, H.S. Tropf, R. Winsky, H. van den Heuvel, R. Haeb-Umbach, K. Choukri, in: ICASSP, Munich, 1997.","chicago":"Hoege, H., H. S. Tropf, R. Winsky, H. van den Heuvel, Reinhold Haeb-Umbach, and K. Choukri. “European Speech Databases for Telephone Applications.” In <i>ICASSP, Munich</i>, 1997.","ieee":"H. Hoege, H. S. Tropf, R. Winsky, H. van den Heuvel, R. Haeb-Umbach, and K. Choukri, “European Speech Databases for Telephone Applications,” in <i>ICASSP, Munich</i>, 1997.","apa":"Hoege, H., Tropf, H. S., Winsky, R., van den Heuvel, H., Haeb-Umbach, R., &#38; Choukri, K. (1997). European Speech Databases for Telephone Applications. In <i>ICASSP, Munich</i>.","bibtex":"@inproceedings{Hoege_Tropf_Winsky_van den Heuvel_Haeb-Umbach_Choukri_1997, title={European Speech Databases for Telephone Applications}, booktitle={ICASSP, Munich}, author={Hoege, H. and Tropf, H. S. and Winsky, R. and van den Heuvel, H. and Haeb-Umbach, Reinhold and Choukri, K.}, year={1997} }","ama":"Hoege H, Tropf HS, Winsky R, van den Heuvel H, Haeb-Umbach R, Choukri K. European Speech Databases for Telephone Applications. In: <i>ICASSP, Munich</i>. ; 1997.","mla":"Hoege, H., et al. “European Speech Databases for Telephone Applications.” <i>ICASSP, Munich</i>, 1997."},"publication":"ICASSP, Munich","abstract":[{"lang":"eng","text":"The SpeechDat project aims to produce speech databases for all official languages of the European Union and some major dialectal variants and minority languages resulting in 28 speech databases. They will be recorded over fixed and mobile telephone networks. This will provide a realistic basis for training and assessment of both isolated and continuous-speech utterances, employing whole-word or subword approaches, and thus can be used for developing voice driven teleservices including speaker verification. The specification of the databases has been developed jointly, and is essentially the same for each language to facilitate dissemination and use. There will be a controlled variation among the speakers concerning sex, age, dialect, environment of call, etc. The validation of all databases will be carried out centrally. The SpeechDat databases will be transferred to ELRA for distribution. The next databases to be recorded will cover East European languages."}],"language":[{"iso":"eng"}],"_id":"11819","main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/1997/ICASSP_1997_Haeb_paper.pdf"}],"user_id":"44006","author":[{"full_name":"Hoege, H.","last_name":"Hoege","first_name":"H."},{"first_name":"H. S.","last_name":"Tropf","full_name":"Tropf, H. S."},{"full_name":"Winsky, R.","last_name":"Winsky","first_name":"R."},{"full_name":"van den Heuvel, H.","last_name":"van den Heuvel","first_name":"H."},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"},{"last_name":"Choukri","first_name":"K.","full_name":"Choukri, K."}],"status":"public","title":"European Speech Databases for Telephone Applications","year":"1997","date_updated":"2022-01-06T06:51:09Z"},{"date_updated":"2022-01-06T06:51:11Z","author":[{"full_name":"Langmann, Detlev","first_name":"Detlev","last_name":"Langmann"},{"full_name":"Fischer, Alexander","last_name":"Fischer","first_name":"Alexander"},{"last_name":"Wuppermann","first_name":"Friedhelm","full_name":"Wuppermann, Friedhelm"},{"first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242"},{"full_name":"Eisele, Thomas","first_name":"Thomas","last_name":"Eisele"}],"status":"public","year":"1997","title":"Acoustic Front Ends for Speaker-Independent Digit Recognition in Car Environments","user_id":"44006","language":[{"iso":"eng"}],"_id":"11852","main_file_link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/1997/Eurospeech_1997_Haeb_paper.pdf","open_access":"1"}],"abstract":[{"lang":"eng","text":"This paper describes speaker-independent speech recognition experiments concerning acoustic front end processing on a speech database that was recorded in 3 different cars. We investigate different feature analysis approaches (mel-filter bank, mel-cepstrum, perceptually linear predictive coding) and present results with noise compensation techniques based on spectral subtraction. Although the methods employed lead to considerable error rate reduction the error analysis shows that low signal-to-noise ratios are still a problem"}],"citation":{"bibtex":"@inproceedings{Langmann_Fischer_Wuppermann_Haeb-Umbach_Eisele_1997, title={Acoustic Front Ends for Speaker-Independent Digit Recognition in Car Environments}, booktitle={Eurospeech}, author={Langmann, Detlev and Fischer, Alexander and Wuppermann, Friedhelm and Haeb-Umbach, Reinhold and Eisele, Thomas}, year={1997} }","ama":"Langmann D, Fischer A, Wuppermann F, Haeb-Umbach R, Eisele T. Acoustic Front Ends for Speaker-Independent Digit Recognition in Car Environments. In: <i>Eurospeech</i>. ; 1997.","mla":"Langmann, Detlev, et al. “Acoustic Front Ends for Speaker-Independent Digit Recognition in Car Environments.” <i>Eurospeech</i>, 1997.","chicago":"Langmann, Detlev, Alexander Fischer, Friedhelm Wuppermann, Reinhold Haeb-Umbach, and Thomas Eisele. “Acoustic Front Ends for Speaker-Independent Digit Recognition in Car Environments.” In <i>Eurospeech</i>, 1997.","short":"D. Langmann, A. Fischer, F. Wuppermann, R. Haeb-Umbach, T. Eisele, in: Eurospeech, 1997.","ieee":"D. Langmann, A. Fischer, F. Wuppermann, R. Haeb-Umbach, and T. Eisele, “Acoustic Front Ends for Speaker-Independent Digit Recognition in Car Environments,” in <i>Eurospeech</i>, 1997.","apa":"Langmann, D., Fischer, A., Wuppermann, F., Haeb-Umbach, R., &#38; Eisele, T. (1997). Acoustic Front Ends for Speaker-Independent Digit Recognition in Car Environments. In <i>Eurospeech</i>."},"publication":"Eurospeech","oa":"1","department":[{"_id":"54"}],"type":"conference","date_created":"2019-07-12T05:29:30Z"},{"status":"public","title":"Investigation of Acoustic Front Ends for Speaker-Independent Speech Recognition in the Car","year":"1997","author":[{"full_name":"Langmann, Detlev","last_name":"Langmann","first_name":"Detlev"},{"last_name":"Wuppermann","first_name":"Friedhelm","full_name":"Wuppermann, Friedhelm"},{"id":"242","first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold"},{"full_name":"Fischer, A.","first_name":"A.","last_name":"Fischer"},{"first_name":"Thomas","last_name":"Eisele","full_name":"Eisele, Thomas"}],"date_updated":"2022-01-06T06:51:11Z","_id":"11855","language":[{"iso":"eng"}],"user_id":"44006","publication":"Aachener Kolloquium on Signal Theory","citation":{"mla":"Langmann, Detlev, et al. “Investigation of Acoustic Front Ends for Speaker-Independent Speech Recognition in the Car.” <i>Aachener Kolloquium on Signal Theory</i>, 1997.","ama":"Langmann D, Wuppermann F, Haeb-Umbach R, Fischer A, Eisele T. Investigation of Acoustic Front Ends for Speaker-Independent Speech Recognition in the Car. In: <i>Aachener Kolloquium on Signal Theory</i>. ; 1997.","bibtex":"@inproceedings{Langmann_Wuppermann_Haeb-Umbach_Fischer_Eisele_1997, title={Investigation of Acoustic Front Ends for Speaker-Independent Speech Recognition in the Car}, booktitle={Aachener Kolloquium on Signal Theory}, author={Langmann, Detlev and Wuppermann, Friedhelm and Haeb-Umbach, Reinhold and Fischer, A. and Eisele, Thomas}, year={1997} }","apa":"Langmann, D., Wuppermann, F., Haeb-Umbach, R., Fischer, A., &#38; Eisele, T. (1997). Investigation of Acoustic Front Ends for Speaker-Independent Speech Recognition in the Car. In <i>Aachener Kolloquium on Signal Theory</i>.","ieee":"D. Langmann, F. Wuppermann, R. Haeb-Umbach, A. Fischer, and T. Eisele, “Investigation of Acoustic Front Ends for Speaker-Independent Speech Recognition in the Car,” in <i>Aachener Kolloquium on Signal Theory</i>, 1997.","chicago":"Langmann, Detlev, Friedhelm Wuppermann, Reinhold Haeb-Umbach, A. Fischer, and Thomas Eisele. “Investigation of Acoustic Front Ends for Speaker-Independent Speech Recognition in the Car.” In <i>Aachener Kolloquium on Signal Theory</i>, 1997.","short":"D. Langmann, F. Wuppermann, R. Haeb-Umbach, A. Fischer, T. Eisele, in: Aachener Kolloquium on Signal Theory, 1997."},"date_created":"2019-07-12T05:29:34Z","type":"conference","department":[{"_id":"54"}]},{"citation":{"ieee":"T. Eisele, R. Haeb-Umbach, and D. Langmann, “A Comparative Study of Linear Feature Transformation Techniques for Automatic Speech Recognition,” in <i>ICSLP , Philadelphia</i>, 1996.","apa":"Eisele, T., Haeb-Umbach, R., &#38; Langmann, D. (1996). A Comparative Study of Linear Feature Transformation Techniques for Automatic Speech Recognition. In <i>ICSLP , Philadelphia</i>.","chicago":"Eisele, Thomas, Reinhold Haeb-Umbach, and Detlev Langmann. “A Comparative Study of Linear Feature Transformation Techniques for Automatic Speech Recognition.” In <i>ICSLP , Philadelphia</i>, 1996.","short":"T. Eisele, R. Haeb-Umbach, D. Langmann, in: ICSLP , Philadelphia, 1996.","mla":"Eisele, Thomas, et al. “A Comparative Study of Linear Feature Transformation Techniques for Automatic Speech Recognition.” <i>ICSLP , Philadelphia</i>, 1996.","bibtex":"@inproceedings{Eisele_Haeb-Umbach_Langmann_1996, title={A Comparative Study of Linear Feature Transformation Techniques for Automatic Speech Recognition}, booktitle={ICSLP , Philadelphia}, author={Eisele, Thomas and Haeb-Umbach, Reinhold and Langmann, Detlev}, year={1996} }","ama":"Eisele T, Haeb-Umbach R, Langmann D. A Comparative Study of Linear Feature Transformation Techniques for Automatic Speech Recognition. In: <i>ICSLP , Philadelphia</i>. ; 1996."},"publication":"ICSLP , Philadelphia","abstract":[{"text":"Although widely used, there are still open questions concerning which properties of linear discriminant analysis (LDA) account for its success in many speech recognition systems. In order to gain more insight into the nature of the transformation we compare LDA with mel-cepstral feature vectors with respect to the following criteria: decorrelation and ordering property; invariance under linear transforms; automatic learning of dynamical features; and data dependence of the transformation.","lang":"eng"}],"date_created":"2019-07-12T05:27:45Z","department":[{"_id":"54"}],"oa":"1","type":"conference","author":[{"first_name":"Thomas","last_name":"Eisele","full_name":"Eisele, Thomas"},{"id":"242","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold"},{"full_name":"Langmann, Detlev","last_name":"Langmann","first_name":"Detlev"}],"year":"1996","title":"A Comparative Study of Linear Feature Transformation Techniques for Automatic Speech Recognition","status":"public","date_updated":"2022-01-06T06:51:08Z","language":[{"iso":"eng"}],"_id":"11761","main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/1996/ICSLP_1996_Haeb1_paper.pdf"}],"user_id":"44006"},{"publication":"IEEE Workshop on Interactive Voice Technology for Telecommunications Applications","citation":{"apa":"Gamm, S., Haeb-Umbach, R., &#38; Langmann, D. (1996). Findings with the Design of a Command-Based Speech Interface for a Voice Mail System. In <i>IEEE Workshop on Interactive Voice Technology for Telecommunications Applications</i>.","ieee":"S. Gamm, R. Haeb-Umbach, and D. Langmann, “Findings with the Design of a Command-Based Speech Interface for a Voice Mail System,” in <i>IEEE Workshop on Interactive Voice Technology for Telecommunications Applications</i>, 1996.","short":"S. Gamm, R. Haeb-Umbach, D. Langmann, in: IEEE Workshop on Interactive Voice Technology for Telecommunications Applications, 1996.","chicago":"Gamm, Stephan, Reinhold Haeb-Umbach, and Detlev Langmann. “Findings with the Design of a Command-Based Speech Interface for a Voice Mail System.” In <i>IEEE Workshop on Interactive Voice Technology for Telecommunications Applications</i>, 1996.","mla":"Gamm, Stephan, et al. “Findings with the Design of a Command-Based Speech Interface for a Voice Mail System.” <i>IEEE Workshop on Interactive Voice Technology for Telecommunications Applications</i>, 1996.","ama":"Gamm S, Haeb-Umbach R, Langmann D. Findings with the Design of a Command-Based Speech Interface for a Voice Mail System. In: <i>IEEE Workshop on Interactive Voice Technology for Telecommunications Applications</i>. ; 1996.","bibtex":"@inproceedings{Gamm_Haeb-Umbach_Langmann_1996, title={Findings with the Design of a Command-Based Speech Interface for a Voice Mail System}, booktitle={IEEE Workshop on Interactive Voice Technology for Telecommunications Applications}, author={Gamm, Stephan and Haeb-Umbach, Reinhold and Langmann, Detlev}, year={1996} }"},"abstract":[{"lang":"eng","text":"This paper tells the story of the design of a command-based speech interface for a voice mail system. Speech recognition was integrated in the voice mail system in order to allow the remote interrogation of messages in a speech-only dialogue. Our design goal was that consumers would perceive voice control as a clear benefit versus touch-tone control. It is shown how the speech interface was designed in a top-down approach. We started with a concept development and tested it by means of a Wizard-of-Oz simulation. After refining the concept in parallel design, the design was implemented in a high-fidelity prototype. By means of qualitative user testing it was improved in three iteration steps. We verified the achievement of our design goal with tests in two countries"}],"date_created":"2019-07-12T05:27:52Z","type":"conference","department":[{"_id":"54"}],"oa":"1","title":"Findings with the Design of a Command-Based Speech Interface for a Voice Mail System","status":"public","year":"1996","author":[{"full_name":"Gamm, Stephan","last_name":"Gamm","first_name":"Stephan"},{"last_name":"Haeb-Umbach","first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","id":"242"},{"full_name":"Langmann, Detlev","first_name":"Detlev","last_name":"Langmann"}],"date_updated":"2022-01-06T06:51:08Z","main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/1996/Workshop_1996__Haeb_paper.pdf"}],"_id":"11767","language":[{"iso":"eng"}],"user_id":"44006"},{"date_updated":"2022-01-06T06:51:11Z","status":"public","title":"FRESCO: The French Telephone Speech Data Collection - Part of the European SpeechDat(M) Project","year":"1996","author":[{"last_name":"Langmann","first_name":"Detlev","full_name":"Langmann, Detlev"},{"last_name":"Haeb-Umbach","first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","id":"242"}],"user_id":"44006","main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/1996/ICSLP_1996_Haeb_paper.pdf"}],"_id":"11853","language":[{"iso":"eng"}],"abstract":[{"text":"The paper describes the design, collection and postprocessing of the French SpeechDat corpus FRESCO. Being a database of approximately 35000 utterances recorded from 1000 callers over the terrestrial telephone network in France, it comprises immediately usable and relevant speech for the initial training and assessment of speaker independent phoneme model or word model based speech recognizers, as they are employed in automated telephone services. FRESCO is one of the 1000 speaker telephone speech databases produced as \"case studies\" within the European project SpeechDat(M).","lang":"eng"}],"publication":"ICSLP, Philadelphia","citation":{"ieee":"D. Langmann and R. Haeb-Umbach, “FRESCO: The French Telephone Speech Data Collection - Part of the European SpeechDat(M) Project,” in <i>ICSLP, Philadelphia</i>, 1996.","apa":"Langmann, D., &#38; Haeb-Umbach, R. (1996). FRESCO: The French Telephone Speech Data Collection - Part of the European SpeechDat(M) Project. In <i>ICSLP, Philadelphia</i>.","short":"D. Langmann, R. Haeb-Umbach, in: ICSLP, Philadelphia, 1996.","chicago":"Langmann, Detlev, and Reinhold Haeb-Umbach. “FRESCO: The French Telephone Speech Data Collection - Part of the European SpeechDat(M) Project.” In <i>ICSLP, Philadelphia</i>, 1996.","mla":"Langmann, Detlev, and Reinhold Haeb-Umbach. “FRESCO: The French Telephone Speech Data Collection - Part of the European SpeechDat(M) Project.” <i>ICSLP, Philadelphia</i>, 1996.","bibtex":"@inproceedings{Langmann_Haeb-Umbach_1996, title={FRESCO: The French Telephone Speech Data Collection - Part of the European SpeechDat(M) Project}, booktitle={ICSLP, Philadelphia}, author={Langmann, Detlev and Haeb-Umbach, Reinhold}, year={1996} }","ama":"Langmann D, Haeb-Umbach R. FRESCO: The French Telephone Speech Data Collection - Part of the European SpeechDat(M) Project. In: <i>ICSLP, Philadelphia</i>. ; 1996."},"type":"conference","department":[{"_id":"54"}],"oa":"1","date_created":"2019-07-12T05:29:31Z"},{"department":[{"_id":"54"}],"type":"conference","date_created":"2019-07-12T05:29:32Z","citation":{"chicago":"Langmann, Detlev, Reinhold Haeb-Umbach, and Thomas Eisele. “Robust Rejection Modeling for a Small-Vocabulary Application.” In <i>ITG Fachtagung Sprachkommunikation, Frankfurt</i>, 1996.","short":"D. Langmann, R. Haeb-Umbach, T. Eisele, in: ITG Fachtagung Sprachkommunikation, Frankfurt, 1996.","ieee":"D. Langmann, R. Haeb-Umbach, and T. Eisele, “Robust Rejection Modeling for a Small-Vocabulary Application,” in <i>ITG Fachtagung Sprachkommunikation, Frankfurt</i>, 1996.","apa":"Langmann, D., Haeb-Umbach, R., &#38; Eisele, T. (1996). Robust Rejection Modeling for a Small-Vocabulary Application. In <i>ITG Fachtagung Sprachkommunikation, Frankfurt</i>.","bibtex":"@inproceedings{Langmann_Haeb-Umbach_Eisele_1996, title={Robust Rejection Modeling for a Small-Vocabulary Application}, booktitle={ITG Fachtagung Sprachkommunikation, Frankfurt}, author={Langmann, Detlev and Haeb-Umbach, Reinhold and Eisele, Thomas}, year={1996} }","ama":"Langmann D, Haeb-Umbach R, Eisele T. Robust Rejection Modeling for a Small-Vocabulary Application. In: <i>ITG Fachtagung Sprachkommunikation, Frankfurt</i>. ; 1996.","mla":"Langmann, Detlev, et al. “Robust Rejection Modeling for a Small-Vocabulary Application.” <i>ITG Fachtagung Sprachkommunikation, Frankfurt</i>, 1996."},"publication":"ITG Fachtagung Sprachkommunikation, Frankfurt","user_id":"44006","_id":"11854","language":[{"iso":"eng"}],"date_updated":"2022-01-06T06:51:11Z","author":[{"last_name":"Langmann","first_name":"Detlev","full_name":"Langmann, Detlev"},{"id":"242","first_name":"Reinhold","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold"},{"last_name":"Eisele","first_name":"Thomas","full_name":"Eisele, Thomas"}],"title":"Robust Rejection Modeling for a Small-Vocabulary Application","status":"public","year":"1996"},{"date_created":"2019-07-12T05:27:40Z","type":"conference","oa":"1","department":[{"_id":"54"}],"publication":"ICASSP, Detroit","citation":{"apa":"Dugast, C., Beyerlein, P., &#38; Haeb-Umbach, R. (1995). Application of Clustering Techniques to Mixture Density Modelling for Continuous-Speech Recognition. In <i>ICASSP, Detroit</i>.","ieee":"C. Dugast, P. Beyerlein, and R. Haeb-Umbach, “Application of Clustering Techniques to Mixture Density Modelling for Continuous-Speech Recognition,” in <i>ICASSP, Detroit</i>, 1995.","chicago":"Dugast, Christian, Peter Beyerlein, and Reinhold Haeb-Umbach. “Application of Clustering Techniques to Mixture Density Modelling for Continuous-Speech Recognition.” In <i>ICASSP, Detroit</i>, 1995.","short":"C. Dugast, P. Beyerlein, R. Haeb-Umbach, in: ICASSP, Detroit, 1995.","mla":"Dugast, Christian, et al. “Application of Clustering Techniques to Mixture Density Modelling for Continuous-Speech Recognition.” <i>ICASSP, Detroit</i>, 1995.","ama":"Dugast C, Beyerlein P, Haeb-Umbach R. Application of Clustering Techniques to Mixture Density Modelling for Continuous-Speech Recognition. In: <i>ICASSP, Detroit</i>. ; 1995.","bibtex":"@inproceedings{Dugast_Beyerlein_Haeb-Umbach_1995, title={Application of Clustering Techniques to Mixture Density Modelling for Continuous-Speech Recognition}, booktitle={ICASSP, Detroit}, author={Dugast, Christian and Beyerlein, Peter and Haeb-Umbach, Reinhold}, year={1995} }"},"abstract":[{"lang":"eng","text":"Clustering techniques have been integrated at different levels into the training procedure of a continuous-density hidden Markov model (HMM) speech recognizer. These clustering techniques can be used in two ways. First acoustically similar states are tied together. It will help to reduce the number of parameters but also allow to train otherwise rarely seen states together with more robust ones (state-tying). Secondly densities are clustered across states, this reduces the number of densities while at the same time keeping the best performances of our recognizer (density-clustering). We have applied these techniques both to word-based small-vocabulary and phoneme-based large-vocabulary recognition tasks. On the WSJ task, we could achieve a reduction of the word error rate by 7%. On the TI/NIST-connected digit task, the number of parameters was reduced by a factor 2-3 while keeping the same string error rate."}],"main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/1995/ICASSP_1995_Haeb_paper.pdf"}],"language":[{"iso":"eng"}],"_id":"11757","user_id":"44006","status":"public","year":"1995","title":"Application of Clustering Techniques to Mixture Density Modelling for Continuous-Speech Recognition","author":[{"full_name":"Dugast, Christian","first_name":"Christian","last_name":"Dugast"},{"first_name":"Peter","last_name":"Beyerlein","full_name":"Beyerlein, Peter"},{"full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","first_name":"Reinhold","id":"242"}],"date_updated":"2022-01-06T06:51:08Z"},{"publication":"Philips Journal of Research","citation":{"ieee":"S. Gamm and R. Haeb-Umbach, “User interface design of voice controlled consumer electronics,” <i>Philips Journal of Research</i>, 1995.","apa":"Gamm, S., &#38; Haeb-Umbach, R. (1995). User interface design of voice controlled consumer electronics. <i>Philips Journal of Research</i>.","mla":"Gamm, Stephan, and Reinhold Haeb-Umbach. “User Interface Design of Voice Controlled Consumer Electronics.” <i>Philips Journal of Research</i>, 1995.","bibtex":"@article{Gamm_Haeb-Umbach_1995, title={User interface design of voice controlled consumer electronics}, journal={Philips Journal of Research}, author={Gamm, Stephan and Haeb-Umbach, Reinhold}, year={1995} }","chicago":"Gamm, Stephan, and Reinhold Haeb-Umbach. “User Interface Design of Voice Controlled Consumer Electronics.” <i>Philips Journal of Research</i>, 1995.","short":"S. Gamm, R. Haeb-Umbach, Philips Journal of Research (1995).","ama":"Gamm S, Haeb-Umbach R. User interface design of voice controlled consumer electronics. <i>Philips Journal of Research</i>. 1995."},"abstract":[{"text":"Today speech recognition of a small vocabulary can be realized so cost-effectively that the technology can penetrate into consumer electronics. But, as first applications that failed on the market show, it is by no means obvious how to incorporate voice control in a user interface. This paper addresses the issue of how to design a voice control so that the user perceives it as a benefit. User interface guidelines that are adapted or specific to voice control are presented. Then the process of designing a voice control in the user-centred approach is described. By means of two examples, the car stereo and telephone answering machine, it is shown how this is turned into practice.","lang":"eng"}],"date_created":"2019-07-12T05:27:48Z","type":"journal_article","department":[{"_id":"54"}],"title":"User interface design of voice controlled consumer electronics","status":"public","year":"1995","author":[{"full_name":"Gamm, Stephan","first_name":"Stephan","last_name":"Gamm"},{"full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold","last_name":"Haeb-Umbach","id":"242"}],"date_updated":"2022-01-06T06:51:08Z","_id":"11764","language":[{"iso":"eng"}],"user_id":"44006"}]