{"main_file_link":[{"open_access":"1","url":"https://groups.uni-paderborn.de/nt/pubs/2009/LeHa09-2.pdf"}],"oa":"1","department":[{"_id":"54"}],"publication":"Interspeech 2009","date_created":"2019-07-12T05:29:39Z","citation":{"bibtex":"@inproceedings{Leutnant_Haeb-Umbach_2009, title={An analytic derivation of a phase-sensitive observation model for noise robust speech recognition}, booktitle={Interspeech 2009}, author={Leutnant, Volker and Haeb-Umbach, Reinhold}, year={2009} }","apa":"Leutnant, V., &#38; Haeb-Umbach, R. (2009). An analytic derivation of a phase-sensitive observation model for noise robust speech recognition. In <i>Interspeech 2009</i>.","ama":"Leutnant V, Haeb-Umbach R. An analytic derivation of a phase-sensitive observation model for noise robust speech recognition. In: <i>Interspeech 2009</i>. ; 2009.","short":"V. Leutnant, R. Haeb-Umbach, in: Interspeech 2009, 2009.","ieee":"V. Leutnant and R. Haeb-Umbach, “An analytic derivation of a phase-sensitive observation model for noise robust speech recognition,” in <i>Interspeech 2009</i>, 2009.","chicago":"Leutnant, Volker, and Reinhold Haeb-Umbach. “An Analytic Derivation of a Phase-Sensitive Observation Model for Noise Robust Speech Recognition.” In <i>Interspeech 2009</i>, 2009.","mla":"Leutnant, Volker, and Reinhold Haeb-Umbach. “An Analytic Derivation of a Phase-Sensitive Observation Model for Noise Robust Speech Recognition.” <i>Interspeech 2009</i>, 2009."},"abstract":[{"lang":"eng","text":"In this paper we present an analytic derivation of the moments of the phase factor between clean speech and noise cepstral or log-mel-spectral feature vectors. The development shows, among others, that the probability density of the phase factor is of sub-Gaussian nature and that it is independent of the noise type and the signal-to-noise ratio, however dependent on the mel filter bank index. Further we show how to compute the contribution of the phase factor to both the mean and the vari- ance of the noisy speech observation likelihood, which relates the speech and noise feature vectors to those of noisy speech. The resulting phase-sensitive observation model is then used in model-based speech feature enhancement, leading to significant improvements in word accuracy on the AURORA2 database."}],"language":[{"iso":"eng"}],"_id":"11860","year":"2009","user_id":"44006","type":"conference","date_updated":"2022-01-06T06:51:11Z","title":"An analytic derivation of a phase-sensitive observation model for noise robust speech recognition","status":"public","author":[{"first_name":"Volker","last_name":"Leutnant","full_name":"Leutnant, Volker"},{"full_name":"Haeb-Umbach, Reinhold","id":"242","first_name":"Reinhold","last_name":"Haeb-Umbach"}]}