{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T20:58:47Z","timestamp":1774645127040,"version":"3.50.1"},"reference-count":42,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383464","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T16:46:54Z","timestamp":1616690814000},"page":"801-808","source":"Crossref","is-referenced-by-count":21,"title":["Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks"],"prefix":"10.1109","author":[{"given":"Max W. Y.","family":"Lam","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472805"},{"key":"ref38","article-title":"Experiments on parallel training of deep neural network using model averaging","author":"su","year":"2015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1629"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref31","article-title":"Continuous speech recognition (csr-i) wall street journal (wsj0) news, complete. linguistic data consortium, philadelphia (1993)","author":"garofalo","year":"0"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2181"},{"key":"ref37","article-title":"Automatic differentiation in PyTorch","author":"paszke","year":"2017","journal-title":"NIPS Autodiff Workshop"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054719"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37731-1_53"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref40","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937186"},{"key":"ref13","article-title":"T-gsa: Transformer with gaussian-weighted self-attention for speech enhancement","author":"kim","year":"2019"},{"key":"ref14","article-title":"Wave-u-net: A multi-scale neural network for end-to-end audio source separation","author":"stoller","year":"2018","journal-title":"19th International Society for Music Information Retrieval Conference ISMIR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1049\/cp:19991218"},{"key":"ref16","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014"},{"key":"ref17","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref28","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682061"},{"key":"ref27","first-page":"3165","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2941148"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003849"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054127"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref2","article-title":"Dual-path rnn: efficient long sequence modeling for time-domain single-channel speech separation","author":"luo","year":"2019"},{"key":"ref9","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"bai","year":"2018"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907229"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2702"},{"key":"ref22","article-title":"Simplified self-attention for transformer-based end-to-end speech recognition","author":"luo","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1973"},{"key":"ref42","article-title":"Gradient flow in recurrent nets: the difficulty of learning long-term dependencies","author":"hochreiter","year":"2001"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2762739"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1027"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref25","article-title":"R-transformer: Recurrent neural network enhanced transformer","author":"wang","year":"2019"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","location":"Shenzhen, China","start":{"date-parts":[[2021,1,19]]},"end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383464.pdf?arnumber=9383464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,31]],"date-time":"2021-05-31T17:31:05Z","timestamp":1622482265000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383464\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383464","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}