{"publication":"ICASSP, Minneapolis","type":"conference","date_updated":"2022-01-06T06:51:07Z","main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/1993/ICASSP_1993_Haeb1_paper.pdf"}],"language":[{"iso":"eng"}],"department":[{"_id":"54"}],"title":"Continuous Mixture Densities and Linear Discriminant Analysis for Improved Context-Dependent Acoustic Models","_id":"11718","date_created":"2019-07-12T05:26:55Z","citation":{"chicago":"Aubert, Xavier L., Reinhold Haeb-Umbach, and Hermann Ney. “Continuous Mixture Densities and Linear Discriminant Analysis for Improved Context-Dependent Acoustic Models.” In <i>ICASSP, Minneapolis</i>, 1993.","apa":"Aubert, X. L., Haeb-Umbach, R., &#38; Ney, H. (1993). Continuous Mixture Densities and Linear Discriminant Analysis for Improved Context-Dependent Acoustic Models. In <i>ICASSP, Minneapolis</i>.","short":"X.L. Aubert, R. Haeb-Umbach, H. Ney, in: ICASSP, Minneapolis, 1993.","ieee":"X. L. Aubert, R. Haeb-Umbach, and H. Ney, “Continuous Mixture Densities and Linear Discriminant Analysis for Improved Context-Dependent Acoustic Models,” in <i>ICASSP, Minneapolis</i>, 1993.","ama":"Aubert XL, Haeb-Umbach R, Ney H. Continuous Mixture Densities and Linear Discriminant Analysis for Improved Context-Dependent Acoustic Models. In: <i>ICASSP, Minneapolis</i>. ; 1993.","mla":"Aubert, Xavier L., et al. “Continuous Mixture Densities and Linear Discriminant Analysis for Improved Context-Dependent Acoustic Models.” <i>ICASSP, Minneapolis</i>, 1993.","bibtex":"@inproceedings{Aubert_Haeb-Umbach_Ney_1993, title={Continuous Mixture Densities and Linear Discriminant Analysis for Improved Context-Dependent Acoustic Models}, booktitle={ICASSP, Minneapolis}, author={Aubert, Xavier L. and Haeb-Umbach, Reinhold and Ney, Hermann}, year={1993} }"},"user_id":"44006","year":"1993","status":"public","oa":"1","abstract":[{"text":"Linear discriminant analysis (LDA) experiments reported previously (ICASSP-92 vol.1, p.13-16), are extended to context-dependent models and speaker-independent large vocabulary continuous speech recognition. Two variants of using mixture densities are compared: state-specific modeling and the monophone-tying approach where densities are shared across the states relevant to the same phoneme. Results are presented on the DARPA Resource Management (RM) task for both speaker-dependent (SD) and speaker-independent (SI) parts. Using triphone models based on LDA and continuous mixture densities, significant improvements have been observed and the following word error rates have been achieved: for the SD part, 7.8% without grammar and 1.5% with word pair; and for the SI part, 17.2% and 4.6%, respectively. These scores are averaged over 1200 SD or SI evaluation sentences and are among the best published so far on the RM database.","lang":"eng"}],"author":[{"first_name":"Xavier L.","last_name":"Aubert","full_name":"Aubert, Xavier L."},{"full_name":"Haeb-Umbach, Reinhold","last_name":"Haeb-Umbach","id":"242","first_name":"Reinhold"},{"first_name":"Hermann","full_name":"Ney, Hermann","last_name":"Ney"}]}