{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:54:59Z","timestamp":1776887699422,"version":"3.51.2"},"reference-count":28,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462661","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"5554-5558","source":"Crossref","is-referenced-by-count":113,"title":["Single Channel Target Speaker Extraction and Recognition with Speaker Beam"],"prefix":"10.1109","author":[{"given":"Marc","family":"Delcroix","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katerina","family":"Zmolikova","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keisuke","family":"Kinoshita","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atsunori","family":"Ogawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomohiro","family":"Nakatani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2444659"},{"key":"ref11","article-title":"Deep attractor network for single-microphone speaker separation","author":"chen","year":"2017","journal-title":"Proc ICASSP'17"},{"key":"ref12","article-title":"Permutation invariant training of deep models for speaker-independent multi-talker speech separation","author":"dong","year":"2017","journal-title":"Proc ICASSP'17"},{"key":"ref13","author":"chen","year":"2017","journal-title":"Progressive joint modeling in unsupervised single-channel overlapped speech recognition"},{"key":"ref14","article-title":"Joint separation and denoising of noisy multi-talker speech using recurrent neural networks and permutation invariant training","author":"kolbaek","year":"2017","journal-title":"Proc of MLSP'17"},{"key":"ref15","author":"qian","year":"2017","journal-title":"Single-channel multi-talker speech recognition with permutation invariant training"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-667","article-title":"Speaker-aware neural network based beamformer for speaker extraction in speech mixtures","author":"zmolikova","year":"2017","journal-title":"Proc of Interspeech 17"},{"key":"ref17","first-page":"5270","article-title":"Context adaptive deep neural networks for fast acoustic model adaptation in noisy conditions","author":"delcroix","year":"2016","journal-title":"Proc of ICASSP'16 IEEE"},{"key":"ref18","article-title":"Learning speaker representation for neural network based multichannel speaker extraction","author":"zmolikova","year":"2017","journal-title":"Proc of ASRU'17"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178829"},{"key":"ref28","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-552"},{"key":"ref27","author":"garofolo","year":"1993","journal-title":"CSR-I (WSJ0) Complete LDC93S6A"},{"key":"ref3","first-page":"196","article-title":"Neural network based spectral mask estimation for acoustic beamforming","author":"heymann","year":"2016","journal-title":"Proc ICASSP'16"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2672401"},{"key":"ref5","article-title":"Deep beamforming networks for multi-channel speech recognition","author":"xiao","year":"2016","journal-title":"Proc ICASSP'16"},{"key":"ref8","author":"wang","year":"2017","journal-title":"Supervised speech separation based on deep learning an overview"},{"key":"ref7","year":"2017","journal-title":"The 4th CHiME speech separation and recognition challenge"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64680-0"},{"key":"ref9","first-page":"31","article-title":"Deep clustering: Discriminative embeddings for segmentation and separation","author":"hershey","year":"2016","journal-title":"Proc ICASSP'16"},{"key":"ref1","first-page":"745","article-title":"An overview of noise-robust automatic speech recognition","volume":"22","author":"li","year":"2014","journal-title":"IEEE Trans ASLP"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472692"},{"key":"ref22","first-page":"92","article-title":"Improving robustness of deep neural network acoustic models via speech separation and joint adaptive training","volume":"23","author":"narayanan","year":"2015","journal-title":"IEEE Trans on ASLP"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2008.11.001"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1570","article-title":"Robust speech recognition via anchor word representations","author":"king","year":"2017","journal-title":"Proc of Interspeech 17"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref26","article-title":"Optimization of speaker-aware multichannel speaker extraction with asr criterion","author":"zmolikova","year":"2018","journal-title":"Proc IEEE ICASSP'18"},{"key":"ref25","first-page":"5325","article-title":"Beamnet: End-to-end training of a beamformer-supported multi-channel asr system","author":"heymann","year":"2017","journal-title":"Proc ICASSP'17"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Calgary, AB","start":{"date-parts":[[2018,4,15]]},"end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08462661.pdf?arnumber=8462661","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T00:56:17Z","timestamp":1598230577000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462661\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462661","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}