{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:25:57Z","timestamp":1775229957583,"version":"3.50.1"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746885","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7297-7301","source":"Crossref","is-referenced-by-count":9,"title":["Mixed Precision DNN Quantization for Overlapped Speech Separation and Recognition"],"prefix":"10.1109","author":[{"given":"Junhao","family":"Xu","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwei","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent AI lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xunying","family":"Liu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Ternary weight networks","author":"li","year":"2016","journal-title":"arXiv preprint arXiv 1605 04711"},{"key":"ref38","article-title":"Xnor-net: Imagenet classification using binary convolutional neural networks","author":"rastegari","year":"2016","journal-title":"ECCV"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref32","article-title":"End-to-end multi-channel speech separation","author":"gu","year":"2019","journal-title":"arXiv preprint arXiv 1905 09010"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639593"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2284"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref36","article-title":"Complex ratio masking for monaural speech separation","author":"williamson","year":"2015","journal-title":"TASLP"},{"key":"ref35","article-title":"Joint training of complex ratio mask based beam-former and acoustic model for noise robust asr","author":"xu","year":"2019","journal-title":"ICASSP"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2980956"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1944345.1944349"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3015659"},{"key":"ref12","article-title":"Binary neural networks for speech recognition","author":"y","year":"2019","journal-title":"Frontiers of Information Technology & Electronic Engineering"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11713"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003744"},{"key":"ref15","article-title":"Binaryconnect: training deep neural networks with binary weights during propagations","author":"courbariaux","year":"2015","journal-title":"NIPS"},{"key":"ref16","article-title":"Mixed precision training","author":"micikevicius","year":"2018","journal-title":"ICLRE"},{"key":"ref17","article-title":"Mixed-precision training for nlp and speech recognition with openseq2seq","author":"kuchaiev","year":"2018","journal-title":"arXiv preprint arXiv 1805 10387"},{"key":"ref18","article-title":"Low-bit quantization of recurrent neural network language models using alternating direction methods of multi-pliers","author":"xu","year":"2020","journal-title":"ICASSP"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1962"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1192"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1991"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/53.665"},{"key":"ref6","article-title":"On optimal frequency-domain multichannel linear filtering for noise reduction","author":"souden","year":"2009","journal-title":"TASLP"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3082282"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/78.902111"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682470"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414127"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3181"},{"key":"ref20","article-title":"Hawq-v2: Hessian aware trace-weighted quantization of neural networks","author":"dong","year":"2019","journal-title":"NeurIPS"},{"key":"ref22","article-title":"Mixed precision dnns: All you need is a good parametrization","author":"uhlich","year":"2019","journal-title":"ICLRE"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00038"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01210"},{"key":"ref24","article-title":"Mixed precision low-bit quantization of neural net-work language models for speech recognition","author":"xu","year":"2021","journal-title":"TASLP"},{"key":"ref41","article-title":"Neural architecture search: A survey","author":"elsken","year":"2019","journal-title":"J Mach Learn Res"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414076"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3053"},{"key":"ref26","article-title":"Deep audio-visual speech recognition","author":"afouras","year":"2018","journal-title":"TPAMI"},{"key":"ref43","article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","author":"afouras","year":"2018","journal-title":"arXiv preprint arXiv 1809 00496"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3078883"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746885.pdf?arnumber=9746885","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:08:48Z","timestamp":1660594128000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746885\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746885","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}