{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T06:39:28Z","timestamp":1783147168522,"version":"3.54.6"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/jstsp.2024.3524022","type":"journal-article","created":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T19:32:44Z","timestamp":1736278364000},"page":"1544-1556","source":"Crossref","is-referenced-by-count":1,"title":["Latent Mixup Knowledge Distillation for Single Channel Speech Enhancement"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0338-1921","authenticated-orcid":false,"given":"Behnam","family":"Gholami","sequence":"first","affiliation":[{"name":"Samsung Device Solutions Research America, Samsung Semiconductor, Inc., San Diego, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9421-6037","authenticated-orcid":false,"given":"Mostafa","family":"El-Khamy","sequence":"additional","affiliation":[{"name":"Samsung Device Solutions Research America, Samsung Semiconductor, Inc., San Diego, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kee-Bong","family":"Song","sequence":"additional","affiliation":[{"name":"Samsung Device Solutions Research America, Samsung Semiconductor, Inc., San Diego, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"965","article-title":"Speech transformer with data-driven masking for robust speech enhancement","author":"Xu","year":"2021","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"key":"ref2","first-page":"3443","article-title":"Speech enhancement with multi-head self-attention and sinc convolutional neural network","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Audio, Speech, Lang. Process."},{"key":"ref3","first-page":"1051","article-title":"Dual-stream transformer for speech enhancement","author":"Li","year":"2020","journal-title":"IEEE Signal Process. Lett."},{"key":"ref4","first-page":"283","article-title":"A multi-scale LSTM network for speech enhancement","author":"Zhang","year":"2021","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"key":"ref5","first-page":"1504","article-title":"Attention-based LSTM network for speech enhancement","author":"Zhao","year":"2020","journal-title":"IEEE Signal Process. Lett."},{"key":"ref6","first-page":"1090","article-title":"Recurrent neural network with spectral masking for speech enhancement","author":"Xia","year":"2020","journal-title":"IEEE Signal Process. Lett."},{"key":"ref7","first-page":"3190","article-title":"Speech enhancement using gated recurrent unit based recurrent neural networks","author":"Cho","year":"2019","journal-title":"J. Acoust. Soc. Amer."},{"key":"ref8","first-page":"2227","article-title":"A regression approach to speech enhancement based on deep neural networks","volume-title":"Proc. IEEE Int. Conf. Acoustics, Speech, Signal Process.","author":"Xu","year":"2014"},{"issue":"11","key":"ref9","first-page":"5469","article-title":"An LSTM-based speech enhancement system for hearing aids","volume":"29","author":"Zhao","year":"2018","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1924"},{"key":"ref11","first-page":"222","article-title":"Raw waveform-based speech enhancement by fully convolutional networks","volume-title":"Proc. 9th Asia-Pacific Signal Inf. Process. Assoc.","author":"Fu","year":"2018"},{"key":"ref12","first-page":"888","article-title":"Otov2: Automatic, generic, user-friendly","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Chen","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030495"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413536"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3082282"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133209"},{"key":"ref17","first-page":"7297","article-title":"Mixed precision DNN quantization for overlapped speech separation and recognition","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech, Signal Process.","author":"Junhao","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW59220.2023.10193263"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462417"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3195549"},{"key":"ref21","article-title":"WaveNet: A generative model for raw audio","author":"Van Den Oord","year":"2016"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747120"},{"key":"ref23","article-title":"A fully convolutional neural network for speech enhancement","author":"Rim","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054578"},{"key":"ref26","first-page":"227","article-title":"A perceptual weighting filter loss for DNN training in speech enhancement","volume-title":"Proc. IEEE Workshop Appl. Signal Process. Audio Acoust.","author":"Ziyue","year":"2019"},{"key":"ref27","first-page":"3111","article-title":"A fully convolutional neural network for speech enhancement","volume-title":"Proc. IEEE Int. Conf. Acoustics, Speech, Signal Process.","author":"Fu","year":"2018"},{"key":"ref28","first-page":"5069","article-title":"Residual learning for speech enhancement with convolutional neural networks","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech, Signal Process.","author":"Zhao","year":"2021"},{"key":"ref29","first-page":"8271","article-title":"Exploring inter-channel correlation for diversity-preserved knowledge distillation","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Liu","year":"2020"},{"key":"ref30","article-title":"The interspeech 2020 deep noise suppression challenge: Datasets, subjective testing framework, and challenge results","author":"Chandan","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1493"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2913512"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3064421"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683423"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-020-01518-1"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref38","first-page":"1234","article-title":"Mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Zhang","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1539"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533590"},{"key":"ref41","first-page":"1","article-title":"Snrbased teachers-student technique for speech enhancement","volume-title":"Proc. IEEE Int. Conf. Multimedia Expo","author":"Hao","year":"2020"},{"key":"ref42","first-page":"661","article-title":"Teacher-student learning for low-latency online speech enhancement using waveunet","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech, Signal Process.","author":"Nakaoka","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114813"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref45","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref46","article-title":"Fitnets: Hints for thin deep nets","author":"Romero","year":"2014"},{"key":"ref47","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"Zagoruyko","year":"2016"},{"key":"ref48","first-page":"1227","article-title":"Paraphrasing complex network: Network compression via factor transfer","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Kim","year":"2018"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1190"},{"key":"ref50","first-page":"4820","article-title":"Knowledge distillation for smallfootprint highway networks","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech, Signal Process.","author":"Lu","year":"2017"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2442"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1989"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3021711"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1747"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683710"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-517"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_11"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17710"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1097\/AUD.0000000000000028"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-24"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-016-0306-6"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref65","first-page":"227","article-title":"Deep noise suppression challenge","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech, Signal Process.","author":"Dubey","year":"2022"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/mmsp.2018.8547084"},{"key":"ref67","first-page":"2031","article-title":"MetricGAN: Generative adversarial networks based black-box metric scores optimization for speech enhancement","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fu","year":"2019"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6489"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10251"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00816"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114813"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746273"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref74","article-title":"Improved speech enhancement with the Wave-U-Net","author":"Macartney","year":"2018"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413740"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2207"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682834"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3116502"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2021.108499"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref83","article-title":"Conformer: Convolution-augmented transformer for speech recognition","author":"Anmol","year":"2020"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/10874827\/10832563.pdf?arnumber=10832563","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T18:37:38Z","timestamp":1738867058000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832563\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":83,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2024.3524022","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}