{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T16:47:22Z","timestamp":1782578842373,"version":"3.54.5"},"reference-count":28,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Speech Communication"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.specom.2026.103430","type":"journal-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T16:34:51Z","timestamp":1781541291000},"page":"103430","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["DPDFNet: Boosting DeepFilterNet2 via dual-path RNN"],"prefix":"10.1016","volume":"182","author":[{"given":"Daniel","family":"Rika","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nino","family":"Sapir","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ido","family":"Gus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.specom.2026.103430_b1","series-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"10.1016\/j.specom.2026.103430_b2","series-title":"2021 IEEE International Conference on Acoustics, Speech and Signal Processing","article-title":"Towards efficient models for real-time deep noise suppression","author":"Braun","year":"2021"},{"key":"10.1016\/j.specom.2026.103430_b3","series-title":"Interspeech 2020","first-page":"3291","article-title":"Real time speech enhancement in the waveform domain","author":"D\u00e9fossez","year":"2020","ISSN":"https:\/\/id.crossref.org\/issn\/2958-1796","issn-type":"print"},{"key":"10.1016\/j.specom.2026.103430_b4","series-title":"ICASSP","article-title":"ICASSP 2022 deep noise suppression challenge","author":"Dubey","year":"2022"},{"key":"10.1016\/j.specom.2026.103430_b5","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1109\/TASLP.2021.3133208","article-title":"FSD50k: An open dataset of human-labeled sound events","volume":"30","author":"Fonseca","year":"2022","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"key":"10.1016\/j.specom.2026.103430_b6","series-title":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing","article-title":"Fullsubnet: A full-band and sub-band fusion model for real-time single-channel speech enhancement","author":"Hao","year":"2021"},{"key":"10.1016\/j.specom.2026.103430_b7","series-title":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"7867","article-title":"Speech denoising in the waveform domain with self-attention","author":"Kong","year":"2022"},{"key":"10.1016\/j.specom.2026.103430_b8","series-title":"Proc. Interspeech","first-page":"2811","article-title":"DPCRN: Dual-path convolution recurrent network for single channel speech enhancement","author":"Le","year":"2021"},{"key":"10.1016\/j.specom.2026.103430_b9","series-title":"Proc. IEEE ICASSP","first-page":"626","article-title":"SDR \u2013 half-baked or well done?","author":"Le Roux","year":"2019"},{"key":"10.1016\/j.specom.2026.103430_b10","doi-asserted-by":"crossref","unstructured":"Lee, B., Calapodescu, I., Gaido, M., Negri, M., Besacier, L., 2024. Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond. In: Proc. Interspeech 2024.","DOI":"10.21437\/Interspeech.2024-957"},{"key":"10.1016\/j.specom.2026.103430_b11","series-title":"International Conference on Learning Representations","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019"},{"key":"10.1016\/j.specom.2026.103430_b12","series-title":"Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation","author":"Luo","year":"2020"},{"key":"10.1016\/j.specom.2026.103430_b13","series-title":"Interspeech 2021","article-title":"NISQA: A deep CNN-self-attention model for multidimensional speech quality prediction with crowdsourced datasets","author":"Mittag","year":"2021"},{"key":"10.1016\/j.specom.2026.103430_b14","series-title":"Interspeech 2025","first-page":"51","article-title":"Optimized real-time speech enhancement with deep SSMs on raw audio","author":"Pei","year":"2025","ISSN":"https:\/\/id.crossref.org\/issn\/2958-1796","issn-type":"print"},{"key":"10.1016\/j.specom.2026.103430_b15","series-title":"Interspeech 2020","article-title":"MLS: A large-scale multilingual dataset for speech research","author":"Pratap","year":"2020"},{"key":"10.1016\/j.specom.2026.103430_b16","series-title":"ICASSP 2021 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"6493","article-title":"Dnsmos: A non-intrusive perceptual objective speech quality metric to evaluate noise suppressors","author":"Reddy","year":"2021"},{"key":"10.1016\/j.specom.2026.103430_b17","series-title":"ICASSP 2022 IEEE International Conference on Acoustics, Speech and Signal Processing","article-title":"DNSMOS p.835: A non-intrusive perceptual objective speech quality metric to evaluate noise suppressors","author":"Reddy","year":"2022"},{"key":"10.1016\/j.specom.2026.103430_b18","doi-asserted-by":"crossref","unstructured":"Rix, A.W., Beerends, J.G., Hollier, M.P., Hekstra, A.P., 2001. Perceptual Evaluation of Speech Quality (PESQ) \u2013 A New Method for Speech Quality Assessment of Telephone Networks and Codecs. In: Proc. IEEE ICASSP. pp. 749\u2013752.","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"10.1016\/j.specom.2026.103430_b19","series-title":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"971","article-title":"GTCRN: A speech enhancement model requiring ultralow computational resources","author":"Rong","year":"2024"},{"key":"10.1016\/j.specom.2026.103430_b20","series-title":"International Workshop on Acoustic Signal Enhancement","article-title":"DeepFilterNet2: Towards real-time speech enhancement on embedded devices for full-band audio","volume":"Vol. 17","author":"Schr\u00f6ter","year":"2022"},{"key":"10.1016\/j.specom.2026.103430_b21","series-title":"DeepFilterNet: Perceptually motivated real-time speech enhancement","author":"Schr\u00f6ter","year":"2023"},{"key":"10.1016\/j.specom.2026.103430_b22","series-title":"MUSAN: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"issue":"7","key":"10.1016\/j.specom.2026.103430_b23","doi-asserted-by":"crossref","first-page":"2125","DOI":"10.1109\/TASL.2011.2114881","article-title":"An algorithm for intelligibility prediction of time\u2013frequency weighted noisy speech","volume":"19","author":"Taal","year":"2011","journal-title":"IEEE Trans. Audio, Speech, Lang. Process."},{"key":"10.1016\/j.specom.2026.103430_b24","series-title":"9th ISCA Workshop on Speech Synthesis Workshop","first-page":"146","article-title":"Investigating RNN-based speech enhancement methods for noise-robust text-to-speech","author":"Valentini-Botinhao","year":"2016"},{"key":"10.1016\/j.specom.2026.103430_b25","series-title":"A hybrid DSP\/Deep learning approach to real-time full-band speech enhancement","author":"Valin","year":"2018"},{"key":"10.1016\/j.specom.2026.103430_b26","series-title":"Proc. Interspeech","first-page":"2472","article-title":"Dual-signal transformation LSTM network for real-time noise suppression","author":"Westhausen","year":"2020"},{"issue":"3","key":"10.1016\/j.specom.2026.103430_b27","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1109\/TASLP.2015.2512042","article-title":"Complex ratio masking for monaural speech separation","volume":"24","author":"Williamson","year":"2016","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"key":"10.1016\/j.specom.2026.103430_b28","series-title":"Interspeech 2024","first-page":"4868","article-title":"URGENT Challenge: Universality, Robustness, and Generalizability For Speech Enhancement","author":"Zhang","year":"2024","ISSN":"https:\/\/id.crossref.org\/issn\/2958-1796","issn-type":"print"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639326000786?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639326000786?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T16:16:28Z","timestamp":1782576988000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639326000786"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":28,"alternative-id":["S0167639326000786"],"URL":"https:\/\/doi.org\/10.1016\/j.specom.2026.103430","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"DPDFNet: Boosting DeepFilterNet2 via dual-path RNN","name":"articletitle","label":"Article Title"},{"value":"Speech Communication","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.specom.2026.103430","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"103430"}}