{"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/deft-an-dense-frequency-time-attentive","title":"DeFT-AN: Dense Frequency-Time Attentive Network for Multichannel Speech Enhancement","arxiv_id":"2212.07570","date":"2022-12-15","proceeding":null,"authors":["Dongheon Lee","Jung-Woo Choi"],"abstract":"In this study, we propose a dense frequency-time attentive network (DeFT-AN) for multichannel speech enhancement. DeFT-AN is a mask estimation network that predicts a complex spectral masking pattern for suppressing the noise and reverberation embedded in the short-time Fourier transform (STFT) of an input signal. The proposed mask estimation network incorporates three different types of blocks for aggregating information in the spatial, spectral, and temporal dimensions. It utilizes a spectral transformer with a modified feed-forward network and a temporal conformer with sequential dilated convolutions. The use of dense blocks and transformers dedicated to the three different characteristics of audio signals enables more comprehensive enhancement in noisy and reverberant environments. The remarkable performance of DeFT-AN over state-of-the-art multichannel models is demonstrated based on two popular noisy and reverberant datasets in terms of various metrics for speech quality and intelligibility.","url_abs":"https://arxiv.org/abs/2212.07570v5","url_pdf":"https://arxiv.org/pdf/2212.07570v5.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":"deft-an-dense-frequency-time-attentive","repo_url":"https://github.com/donghoney0416/DeFT-AN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"speech-dereverberation","task_name":"Speech Dereverberation"},{"task_slug":"speech-enhancement","task_name":"Speech Enhancement"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-dereverberation-on-spatialized-wsjcam0","task":"Speech Dereverberation","dataset":"spatialized WSJCAM0","model":"DeFT-AN","rank_in_archive_order":1,"of":1,"metrics":{"PESQ":"3.63","SI-SDR":"15.7","STOI":"0.981"},"uses_additional_data":false},{"leaderboard":"/sota/speech-enhancement-on-spatialized-dns","task":"Speech Enhancement","dataset":"spatialized DNS challenge","model":"DeFT-AN","rank_in_archive_order":1,"of":1,"metrics":{"PESQ":"3.01","SI-SDR":"9.9","STOI":"0.924"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}