[{"language":[{"iso":"eng"}],"page":"6827-6831","type":"conference","year":"2013","citation":{"short":"A.H. Abdelaziz, S. Zeiler, D. Kolossa, V. Leutnant, R. Haeb-Umbach, in: Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference On, 2013, pp. 6827–6831.","ieee":"A. H. Abdelaziz, S. Zeiler, D. Kolossa, V. Leutnant, and R. Haeb-Umbach, “GMM-based significance decoding,” in Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on, 2013, pp. 6827–6831.","chicago":"Abdelaziz, Ahmed H., Steffen Zeiler, Dorothea Kolossa, Volker Leutnant, and Reinhold Haeb-Umbach. “GMM-Based Significance Decoding.” In Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference On, 6827–31, 2013. https://doi.org/10.1109/ICASSP.2013.6638984.","ama":"Abdelaziz AH, Zeiler S, Kolossa D, Leutnant V, Haeb-Umbach R. GMM-based significance decoding. In: Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference On. ; 2013:6827-6831. doi:10.1109/ICASSP.2013.6638984","apa":"Abdelaziz, A. H., Zeiler, S., Kolossa, D., Leutnant, V., & Haeb-Umbach, R. (2013). GMM-based significance decoding. In Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on (pp. 6827–6831). https://doi.org/10.1109/ICASSP.2013.6638984","mla":"Abdelaziz, Ahmed H., et al. “GMM-Based Significance Decoding.” Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference On, 2013, pp. 6827–31, doi:10.1109/ICASSP.2013.6638984.","bibtex":"@inproceedings{Abdelaziz_Zeiler_Kolossa_Leutnant_Haeb-Umbach_2013, title={GMM-based significance decoding}, DOI={10.1109/ICASSP.2013.6638984}, booktitle={Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on}, author={Abdelaziz, Ahmed H. and Zeiler, Steffen and Kolossa, Dorothea and Leutnant, Volker and Haeb-Umbach, Reinhold}, year={2013}, pages={6827–6831} }"},"_id":"11716","date_updated":"2022-01-06T06:51:07Z","doi":"10.1109/ICASSP.2013.6638984","publication":"Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on","keyword":["Bayes methods","Gaussian processes","convolution","decision theory","decoding","noise","reverberation","speech coding","speech recognition","Bayesian decision rule","GMM","Gaussian mixture models","additive noise scenarios","automatic speech recognition systems","convolutive noise scenarios","decoding approach","mathematical framework","reverberant environments","significance decoding","speech feature estimation","uncertainty-of-observation techniques","Hidden Markov models","Maximum likelihood decoding","Noise","Speech","Speech recognition","Uncertainty","Uncertainty-of-observation","modified imputation","noise robust speech recognition","significance decoding","uncertainty decoding"],"department":[{"_id":"54"}],"author":[{"last_name":"Abdelaziz","first_name":"Ahmed H.","full_name":"Abdelaziz, Ahmed H."},{"first_name":"Steffen","full_name":"Zeiler, Steffen","last_name":"Zeiler"},{"last_name":"Kolossa","full_name":"Kolossa, Dorothea","first_name":"Dorothea"},{"first_name":"Volker","full_name":"Leutnant, Volker","last_name":"Leutnant"},{"full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold","id":"242","last_name":"Haeb-Umbach"}],"date_created":"2019-07-12T05:26:53Z","status":"public","publication_identifier":{"issn":["1520-6149"]},"abstract":[{"text":"The accuracy of automatic speech recognition systems in noisy and reverberant environments can be improved notably by exploiting the uncertainty of the estimated speech features using so-called uncertainty-of-observation techniques. In this paper, we introduce a new Bayesian decision rule that can serve as a mathematical framework from which both known and new uncertainty-of-observation techniques can be either derived or approximated. The new decision rule in its direct form leads to the new significance decoding approach for Gaussian mixture models, which results in better performance compared to standard uncertainty-of-observation techniques in different additive and convolutive noise scenarios.","lang":"eng"}],"user_id":"44006","title":"GMM-based significance decoding"},{"author":[{"last_name":"Vu","full_name":"Vu, Dang Hai Tran","first_name":"Dang Hai Tran"},{"last_name":"Haeb-Umbach","id":"242","first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold"}],"keyword":["correlation methods","estimation theory","hidden Markov models","iterative methods","probability","spectral analysis","speech processing","2D HMM","SPP estimates","iterative algorithm","posterior probability estimation","spectral correlation","speech presence probability estimation","state-of-the-art SPP estimation algorithm","temporal correlation","turbo principle","two-dimensional hidden Markov model","Correlation","Decoding","Estimation","Iterative decoding","Noise","Speech","Vectors"],"publication":"38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)","department":[{"_id":"54"}],"status":"public","date_created":"2019-07-12T05:30:45Z","publication_identifier":{"issn":["1520-6149"]},"abstract":[{"text":"In this paper we present a speech presence probability (SPP) estimation algorithmwhich exploits both temporal and spectral correlations of speech. To this end, the SPP estimation is formulated as the posterior probability estimation of the states of a two-dimensional (2D) Hidden Markov Model (HMM). We derive an iterative algorithm to decode the 2D-HMM which is based on the turbo principle. The experimental results show that indeed the SPP estimates improve from iteration to iteration, and further clearly outperform another state-of-the-art SPP estimation algorithm.","lang":"eng"}],"user_id":"44006","title":"Using the turbo principle for exploiting temporal and spectral correlations in speech presence probability estimation","language":[{"iso":"eng"}],"year":"2013","type":"conference","citation":{"chicago":"Vu, Dang Hai Tran, and Reinhold Haeb-Umbach. “Using the Turbo Principle for Exploiting Temporal and Spectral Correlations in Speech Presence Probability Estimation.” In 38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013), 863–67, 2013. https://doi.org/10.1109/ICASSP.2013.6637771.","ama":"Vu DHT, Haeb-Umbach R. Using the turbo principle for exploiting temporal and spectral correlations in speech presence probability estimation. In: 38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013). ; 2013:863-867. doi:10.1109/ICASSP.2013.6637771","apa":"Vu, D. H. T., & Haeb-Umbach, R. (2013). Using the turbo principle for exploiting temporal and spectral correlations in speech presence probability estimation. In 38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013) (pp. 863–867). https://doi.org/10.1109/ICASSP.2013.6637771","bibtex":"@inproceedings{Vu_Haeb-Umbach_2013, title={Using the turbo principle for exploiting temporal and spectral correlations in speech presence probability estimation}, DOI={10.1109/ICASSP.2013.6637771}, booktitle={38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)}, author={Vu, Dang Hai Tran and Haeb-Umbach, Reinhold}, year={2013}, pages={863–867} }","mla":"Vu, Dang Hai Tran, and Reinhold Haeb-Umbach. “Using the Turbo Principle for Exploiting Temporal and Spectral Correlations in Speech Presence Probability Estimation.” 38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013), 2013, pp. 863–67, doi:10.1109/ICASSP.2013.6637771.","short":"D.H.T. Vu, R. Haeb-Umbach, in: 38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013), 2013, pp. 863–867.","ieee":"D. H. T. Vu and R. Haeb-Umbach, “Using the turbo principle for exploiting temporal and spectral correlations in speech presence probability estimation,” in 38th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013), 2013, pp. 863–867."},"page":"863-867","_id":"11917","date_updated":"2022-01-06T06:51:12Z","doi":"10.1109/ICASSP.2013.6637771"},{"user_id":"44006","abstract":[{"lang":"eng","text":"In automatic speech recognition, hidden Markov models (HMMs) are commonly used for speech decoding, while switching linear dynamic models (SLDMs) can be employed for a preceding model-based speech feature enhancement. In this paper, these model types are combined in order to obtain a novel iterative speech feature enhancement and recognition architecture. It is shown that speech feature enhancement with SLDMs can be improved by feeding back information from the HMM to the enhancement stage. Two different feedback structures are derived. In the first, the posteriors of the HMM states are used to control the model probabilities of the SLDMs, while in the second they are employed to directly influence the estimate of the speech feature distribution. Both approaches lead to improvements in recognition accuracy both on the AURORA2 and AURORA4 databases compared to non-iterative speech feature enhancement with SLDMs. It is also shown that a combination with uncertainty decoding further enhances performance."}],"volume":17,"date_created":"2019-07-12T05:31:08Z","status":"public","keyword":["AURORA2 databases","AURORA4 databases","automatic speech recognition","feedback structures","hidden Markov models","HMM","iterative methods","iterative speech feature enhancement","model probabilities","speech decoding","speech enhancement","speech feature distribution","speech recognition","switching linear dynamic models"],"publication":"IEEE Transactions on Audio, Speech, and Language Processing","author":[{"last_name":"Windmann","first_name":"Stefan","full_name":"Windmann, Stefan"},{"id":"242","last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","first_name":"Reinhold"}],"issue":"5","_id":"11937","intvolume":" 17","page":"974-984","type":"journal_article","year":"2009","citation":{"apa":"Windmann, S., & Haeb-Umbach, R. (2009). Approaches to Iterative Speech Feature Enhancement and Recognition. IEEE Transactions on Audio, Speech, and Language Processing, 17(5), 974–984. https://doi.org/10.1109/TASL.2009.2014894","ama":"Windmann S, Haeb-Umbach R. Approaches to Iterative Speech Feature Enhancement and Recognition. IEEE Transactions on Audio, Speech, and Language Processing. 2009;17(5):974-984. doi:10.1109/TASL.2009.2014894","chicago":"Windmann, Stefan, and Reinhold Haeb-Umbach. “Approaches to Iterative Speech Feature Enhancement and Recognition.” IEEE Transactions on Audio, Speech, and Language Processing 17, no. 5 (2009): 974–84. https://doi.org/10.1109/TASL.2009.2014894.","mla":"Windmann, Stefan, and Reinhold Haeb-Umbach. “Approaches to Iterative Speech Feature Enhancement and Recognition.” IEEE Transactions on Audio, Speech, and Language Processing, vol. 17, no. 5, 2009, pp. 974–84, doi:10.1109/TASL.2009.2014894.","bibtex":"@article{Windmann_Haeb-Umbach_2009, title={Approaches to Iterative Speech Feature Enhancement and Recognition}, volume={17}, DOI={10.1109/TASL.2009.2014894}, number={5}, journal={IEEE Transactions on Audio, Speech, and Language Processing}, author={Windmann, Stefan and Haeb-Umbach, Reinhold}, year={2009}, pages={974–984} }","short":"S. Windmann, R. Haeb-Umbach, IEEE Transactions on Audio, Speech, and Language Processing 17 (2009) 974–984.","ieee":"S. Windmann and R. Haeb-Umbach, “Approaches to Iterative Speech Feature Enhancement and Recognition,” IEEE Transactions on Audio, Speech, and Language Processing, vol. 17, no. 5, pp. 974–984, 2009."},"main_file_link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/2009/WiHa09-1.pdf","open_access":"1"}],"title":"Approaches to Iterative Speech Feature Enhancement and Recognition","department":[{"_id":"54"}],"doi":"10.1109/TASL.2009.2014894","oa":"1","date_updated":"2022-01-06T06:51:12Z","language":[{"iso":"eng"}]},{"issue":"5","intvolume":" 16","_id":"11820","page":"1047-1060","year":"2008","type":"journal_article","citation":{"short":"V. Ion, R. Haeb-Umbach, IEEE Transactions on Audio, Speech, and Language Processing 16 (2008) 1047–1060.","ieee":"V. Ion and R. Haeb-Umbach, “A Novel Uncertainty Decoding Rule With Applications to Transmission Error Robust Speech Recognition,” IEEE Transactions on Audio, Speech, and Language Processing, vol. 16, no. 5, pp. 1047–1060, 2008.","apa":"Ion, V., & Haeb-Umbach, R. (2008). A Novel Uncertainty Decoding Rule With Applications to Transmission Error Robust Speech Recognition. IEEE Transactions on Audio, Speech, and Language Processing, 16(5), 1047–1060. https://doi.org/10.1109/TASL.2008.925879","ama":"Ion V, Haeb-Umbach R. A Novel Uncertainty Decoding Rule With Applications to Transmission Error Robust Speech Recognition. IEEE Transactions on Audio, Speech, and Language Processing. 2008;16(5):1047-1060. doi:10.1109/TASL.2008.925879","chicago":"Ion, Valentin, and Reinhold Haeb-Umbach. “A Novel Uncertainty Decoding Rule With Applications to Transmission Error Robust Speech Recognition.” IEEE Transactions on Audio, Speech, and Language Processing 16, no. 5 (2008): 1047–60. https://doi.org/10.1109/TASL.2008.925879.","bibtex":"@article{Ion_Haeb-Umbach_2008, title={A Novel Uncertainty Decoding Rule With Applications to Transmission Error Robust Speech Recognition}, volume={16}, DOI={10.1109/TASL.2008.925879}, number={5}, journal={IEEE Transactions on Audio, Speech, and Language Processing}, author={Ion, Valentin and Haeb-Umbach, Reinhold}, year={2008}, pages={1047–1060} }","mla":"Ion, Valentin, and Reinhold Haeb-Umbach. “A Novel Uncertainty Decoding Rule With Applications to Transmission Error Robust Speech Recognition.” IEEE Transactions on Audio, Speech, and Language Processing, vol. 16, no. 5, 2008, pp. 1047–60, doi:10.1109/TASL.2008.925879."},"main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/2008/IoHa08-1.pdf"}],"user_id":"44006","abstract":[{"text":"In this paper, we derive an uncertainty decoding rule for automatic speech recognition (ASR), which accounts for both corrupted observations and inter-frame correlation. The conditional independence assumption, prevalent in hidden Markov model-based ASR, is relaxed to obtain a clean speech posterior that is conditioned on the complete observed feature vector sequence. This is a more informative posterior than one conditioned only on the current observation. The novel decoding is used to obtain a transmission-error robust remote ASR system, where the speech capturing unit is connected to the decoder via an error-prone communication network. We show how the clean speech posterior can be computed for communication links being characterized by either bit errors or packet loss. Recognition results are presented for both distributed and network speech recognition, where in the latter case common voice-over-IP codecs are employed.","lang":"eng"}],"volume":16,"date_created":"2019-07-12T05:28:53Z","status":"public","keyword":["automatic speech recognition","bit errors","codecs","communication links","corrupted observations","decoding","distributed speech recognition","error-prone communication network","feature vector sequence","hidden Markov model-based ASR","hidden Markov models","inter-frame correlation","Internet telephony","network speech recognition","packet loss","speech posterior","speech recognition","transmission error robust speech recognition","uncertainty decoding","voice-over-IP codecs"],"publication":"IEEE Transactions on Audio, Speech, and Language Processing","author":[{"first_name":"Valentin","full_name":"Ion, Valentin","last_name":"Ion"},{"first_name":"Reinhold","full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","id":"242"}],"doi":"10.1109/TASL.2008.925879","oa":"1","date_updated":"2022-01-06T06:51:10Z","language":[{"iso":"eng"}],"title":"A Novel Uncertainty Decoding Rule With Applications to Transmission Error Robust Speech Recognition","department":[{"_id":"54"}]}]