{"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/a-modulation-domain-loss-for-neural-network-1","title":"A Modulation-Domain Loss for Neural-Network-based Real-time Speech Enhancement","arxiv_id":"2102.07330","date":"2021-02-15","proceeding":null,"authors":[],"abstract":"We describe a modulation-domain loss function for deep-learning-based speech enhancement systems. Learnable spectro-temporal receptive fields (STRFs) were adapted to optimize for a speaker identification task. The learned STRFs were then used to calculate a weighted mean-squared error (MSE) in the modulation domain for training a speech enhancement system. Experiments showed that adding the modulation-domain MSE to the MSE in the spectro-temporal domain substantially improved the objective prediction of speech quality and intelligibility for real-time speech enhancement systems without incurring additional computation during inference.","url_abs":"https://arxiv.org/abs/2102.07330v1","url_pdf":"https://arxiv.org/pdf/2102.07330v1.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":"a-modulation-domain-loss-for-neural-network-1","repo_url":"https://github.com/tvuong123/ModulationDomainLoss","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"speaker-identification","task_name":"Speaker Identification"},{"task_slug":"speech-denoising","task_name":"Speech Denoising"},{"task_slug":"speech-enhancement","task_name":"Speech Enhancement"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-enhancement-on-interspeech-2020-deep","task":"Speech Enhancement","dataset":"DNS Challenge","model":"RNN-Modulation","rank_in_archive_order":5,"of":5,"metrics":{"PESQ-WB":"2.75"},"uses_additional_data":false},{"leaderboard":"/sota/speech-enhancement-on-deep-noise-suppression","task":"Speech Enhancement","dataset":"Deep Noise Suppression (DNS) Challenge","model":"RNN-Modulation","rank_in_archive_order":24,"of":36,"metrics":{"PESQ-WB":"2.75"},"uses_additional_data":false},{"leaderboard":"/sota/speech-enhancement-on-demand","task":"Speech Enhancement","dataset":"VoiceBank + DEMAND","model":"real-time-GRU","rank_in_archive_order":41,"of":42,"metrics":{"PESQ (wb)":"2.82"},"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}