{"type":"conference","date_created":"2019-07-12T05:30:36Z","date_updated":"2022-01-06T06:51:12Z","author":[{"full_name":"Tran Vu, Dang Hai","first_name":"Dang Hai","last_name":"Tran Vu"},{"last_name":"Haeb-Umbach","full_name":"Haeb-Umbach, Reinhold","id":"242","first_name":"Reinhold"}],"title":"Blind Speech Separation Exploiting Temporal and Spectral Correlations Using Turbo Decoding of 2D-HMMs","status":"public","user_id":"44006","department":[{"_id":"54"}],"oa":"1","language":[{"iso":"eng"}],"citation":{"bibtex":"@inproceedings{Tran Vu_Haeb-Umbach_2013, title={Blind Speech Separation Exploiting Temporal and Spectral Correlations Using Turbo Decoding of 2D-HMMs}, booktitle={21th European Signal Processing Conference (EUSIPCO 2013)}, author={Tran Vu, Dang Hai and Haeb-Umbach, Reinhold}, year={2013} }","short":"D.H. Tran Vu, R. Haeb-Umbach, in: 21th European Signal Processing Conference (EUSIPCO 2013), 2013.","chicago":"Tran Vu, Dang Hai, and Reinhold Haeb-Umbach. “Blind Speech Separation Exploiting Temporal and Spectral Correlations Using Turbo Decoding of 2D-HMMs.” In <i>21th European Signal Processing Conference (EUSIPCO 2013)</i>, 2013.","ieee":"D. H. Tran Vu and R. Haeb-Umbach, “Blind Speech Separation Exploiting Temporal and Spectral Correlations Using Turbo Decoding of 2D-HMMs,” in <i>21th European Signal Processing Conference (EUSIPCO 2013)</i>, 2013.","apa":"Tran Vu, D. H., &#38; Haeb-Umbach, R. (2013). Blind Speech Separation Exploiting Temporal and Spectral Correlations Using Turbo Decoding of 2D-HMMs. In <i>21th European Signal Processing Conference (EUSIPCO 2013)</i>.","ama":"Tran Vu DH, Haeb-Umbach R. Blind Speech Separation Exploiting Temporal and Spectral Correlations Using Turbo Decoding of 2D-HMMs. In: <i>21th European Signal Processing Conference (EUSIPCO 2013)</i>. ; 2013.","mla":"Tran Vu, Dang Hai, and Reinhold Haeb-Umbach. “Blind Speech Separation Exploiting Temporal and Spectral Correlations Using Turbo Decoding of 2D-HMMs.” <i>21th European Signal Processing Conference (EUSIPCO 2013)</i>, 2013."},"main_file_link":[{"url":"https://groups.uni-paderborn.de/nt/pubs/2013/TrHa2013_01.pdf","open_access":"1"}],"_id":"11909","year":"2013","abstract":[{"text":"We present a novel method to exploit correlations of adjacent time-frequency (TF)-slots for a sparseness-based blind speech separation (BSS) system. Usually, these correlations are exploited by some heuristic smoothing techniques in the post-processing of the estimated soft TF masks. We propose a different approach: Based on our previous work with one-dimensional (1D)-hidden Markov models (HMMs) along the time axis we extend the modeling to two-dimensional (2D)-HMMs to exploit both temporal and spectral correlations in the speech signal. Based on the principles of turbo decoding we solved the complex inference of 2D-HMMs by a modified forward-backward algorithm which operates alternatingly along the time and the frequency axis. Extrinsic information is exchanged between these steps such that increasingly better soft time-frequency masks are obtained, leading to improved speech separation performance in highly reverberant recording conditions.","lang":"eng"}],"related_material":{"link":[{"description":"Presentation","url":"https://groups.uni-paderborn.de/nt/pubs/2013/TrHa2013_01_Presentation.pdf","relation":"supplementary_material"}]},"publication":"21th European Signal Processing Conference (EUSIPCO 2013)"}