{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/real-time-single-channel-dereverberation-and","title":"Real-time Single-channel Dereverberation and Separation with Time-domainAudio Separation Network","arxiv_id":null,"date":"2018-09-02","proceeding":"ISCA Interspeech 2018 9","authors":["Yi Luo","Nima Mesgarani"],"abstract":"We investigate the recently proposed Time-domain Audio Sep-aration  Network  (TasNet)  in  the  task  of  real-time  single-channel speech dereverberation. Unlike systems that take time-frequency representation of the audio as input, TasNet learns anadaptive  front-end  in  replacement  of  the  time-frequency  rep-resentation  by  a  time-domain  convolutional  non-negative  au-toencoder.   We  show  that  by  formulating  the  dereverberationproblem as a denoising problem where the direct path is sepa-rated from the reverberations, a TasNet denoising autoencodercan outperform a deep LSTM baseline on log-power magnitudespectrogram input in both causal and non-causal settings.  Wefurther show that adjusting the stride size in the convolutionalautoencoder helps both the dereverberation and separation per-formance.","url_abs":"https://www.isca-speech.org/archive/Interspeech_2018/pdfs/2290.pdf","url_pdf":"https://www.isca-speech.org/archive/Interspeech_2018/pdfs/2290.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"real-time-single-channel-dereverberation-and","repo_url":"https://github.com/mpariente/asteroid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"speech-dereverberation","task_name":"Speech Dereverberation"},{"task_slug":"speech-separation","task_name":"Speech Separation"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-separation-on-wsj0-2mix","task":"Speech Separation","dataset":"WSJ0-2mix","model":"TasNet v2","rank_in_archive_order":37,"of":40,"metrics":{"SI-SDRi":"13.2"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}