{"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-speech-enhancement-in-the-waveform","title":"Real Time Speech Enhancement in the Waveform Domain","arxiv_id":"2006.12847","date":"2020-06-23","proceeding":null,"authors":["Alexandre Defossez","Gabriel Synnaeve","Yossi Adi"],"abstract":"We present a causal speech enhancement model working on the raw waveform that runs in real-time on a laptop CPU. The proposed model is based on an encoder-decoder architecture with skip-connections. It is optimized on both time and frequency domains, using multiple loss functions. Empirical evidence shows that it is capable of removing various kinds of background noise including stationary and non-stationary noises, as well as room reverb. Additionally, we suggest a set of data augmentation techniques applied directly on the raw waveform which further improve model performance and its generalization abilities. We perform evaluations on several standard benchmarks, both using objective metrics and human judgements. The proposed model matches state-of-the-art performance of both causal and non causal methods while working directly on the raw waveform.","url_abs":"https://arxiv.org/abs/2006.12847v3","url_pdf":"https://arxiv.org/pdf/2006.12847v3.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-speech-enhancement-in-the-waveform","repo_url":"https://github.com/facebookresearch/denoiser","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"real-time-speech-enhancement-in-the-waveform","repo_url":"https://github.com/yunyangzeng/taploss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"real-time-speech-enhancement-in-the-waveform","repo_url":"https://github.com/jonashaag/paperswithcode-speech-enhancement-audiosamples/tree/master/Real%20Time%20Speech%20Enhancement%20in%20the%20Waveform%20Domain","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"speech-enhancement","task_name":"Speech Enhancement"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-enhancement-on-demand","task":"Speech Enhancement","dataset":"VoiceBank + DEMAND","model":"DEMUCS (H=64, S=2 ,U =2)","rank_in_archive_order":30,"of":42,"metrics":{"CBAK":"3.4","COVL":"3.63","CSIG":"4.31","PESQ (wb)":"3.07","STOI":"95"},"uses_additional_data":false},{"leaderboard":"/sota/speech-enhancement-on-demand","task":"Speech Enhancement","dataset":"VoiceBank + DEMAND","model":"Causal DEMUCS (H=48,S=4, U =4)","rank_in_archive_order":37,"of":42,"metrics":{"CBAK":"3.25","COVL":"3.52","CSIG":"4.22","PESQ (wb)":"2.93","STOI":"95"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.12847","atlas_url":"https://app.syntology.ai/?focus=2006.12847","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.12847"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/denoiser","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jonashaag/paperswithcode-speech-enhancement-audiosamples/tree/master/Real%20Time%20Speech%20Enhancement%20in%20the%20Waveform%20Domain","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yunyangzeng/taploss","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"a3f6340c5c08fa27","entry":"get_estimate","repo":"facebookresearch/denoiser","repo_kind":"official","path":"denoiser/enhance.py","file_url":"https://github.com/facebookresearch/denoiser/blob/HEAD/denoiser/enhance.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a3f6340c5c08fa27"}},{"code_sha256_prefix":"764208d203a0b06f","entry":"get_dataset","repo":"facebookresearch/denoiser","repo_kind":"official","path":"denoiser/enhance.py","file_url":"https://github.com/facebookresearch/denoiser/blob/HEAD/denoiser/enhance.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"764208d203a0b06f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}