{"id":"https://openalex.org/W3015225820","doi":"https://doi.org/10.1109/icassp40776.2020.9053845","title":"Improving Voice Separation by Incorporating End-To-End Speech Recognition","display_name":"Improving Voice Separation by Incorporating End-To-End Speech Recognition","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015225820","doi":"https://doi.org/10.1109/icassp40776.2020.9053845","mag":"3015225820"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101589290","display_name":"Naoya Takahashi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Naoya Takahashi","raw_affiliation_strings":["Sony Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Corporation, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104006195","display_name":"Mayank Kumar Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mayank Kumar Singh","raw_affiliation_strings":["Indian Institute of Technology Bombay, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082753194","display_name":"Sakya Basak","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sakya Basak","raw_affiliation_strings":["Indian Institute of Science, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022669956","display_name":"Parthasaarathy Sudarsanam","orcid":"https://orcid.org/0009-0009-3751-6469"},"institutions":[{"id":"https://openalex.org/I4210090636","display_name":"Wipro (India)","ror":"https://ror.org/001ccf545","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210090636"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Parthasaarathy Sudarsanam","raw_affiliation_strings":["Sony India Software Centre, India"],"affiliations":[{"raw_affiliation_string":"Sony India Software Centre, India","institution_ids":["https://openalex.org/I4210090636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002536077","display_name":"Sriram Ganapathy","orcid":"https://orcid.org/0000-0002-5779-9066"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sriram Ganapathy","raw_affiliation_strings":["Indian Institute of Science, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088754502","display_name":"Yuki Mitsufuji","orcid":"https://orcid.org/0000-0002-6806-6140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuki Mitsufuji","raw_affiliation_strings":["Sony Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Corporation, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101589290"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3338,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.92962475,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"45"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7782731652259827},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7564046382904053},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7289465665817261},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6251060962677002},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5508404970169067},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.524546205997467},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5185283422470093},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4408305585384369},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4258950650691986},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4221228361129761},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4185711145401001},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3582160472869873},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3251946270465851},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20314082503318787},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.15283161401748657},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09463021159172058}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7782731652259827},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7564046382904053},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7289465665817261},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6251060962677002},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5508404970169067},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.524546205997467},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5185283422470093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4408305585384369},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4258950650691986},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4221228361129761},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4185711145401001},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3582160472869873},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3251946270465851},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20314082503318787},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.15283161401748657},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09463021159172058},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W46110029","https://openalex.org/W185399533","https://openalex.org/W1494198834","https://openalex.org/W1496920063","https://openalex.org/W1515206890","https://openalex.org/W1522734439","https://openalex.org/W2036245667","https://openalex.org/W2087681821","https://openalex.org/W2088361146","https://openalex.org/W2129116669","https://openalex.org/W2155541015","https://openalex.org/W2221409856","https://openalex.org/W2395107641","https://openalex.org/W2398264106","https://openalex.org/W2570915410","https://openalex.org/W2593116425","https://openalex.org/W2734774145","https://openalex.org/W2766219058","https://openalex.org/W2889134433","https://openalex.org/W2892365986","https://openalex.org/W2916985722","https://openalex.org/W2962780374","https://openalex.org/W2962833129","https://openalex.org/W2963750251","https://openalex.org/W2963751183","https://openalex.org/W2963992487","https://openalex.org/W2964171275","https://openalex.org/W2972492143","https://openalex.org/W2972541922","https://openalex.org/W2972767900","https://openalex.org/W3123318516","https://openalex.org/W4289665794","https://openalex.org/W4294375521","https://openalex.org/W6629717138","https://openalex.org/W6631456553","https://openalex.org/W6679489070","https://openalex.org/W6682778277","https://openalex.org/W6688843265","https://openalex.org/W6752109149","https://openalex.org/W6754743415","https://openalex.org/W6759212570"],"related_works":["https://openalex.org/W2294333436","https://openalex.org/W2373767407","https://openalex.org/W2653598178","https://openalex.org/W2747006289","https://openalex.org/W4252682934","https://openalex.org/W2851491717","https://openalex.org/W2072884270","https://openalex.org/W2356426224","https://openalex.org/W2734909224","https://openalex.org/W4386474880"],"abstract_inverted_index":{"Despite":[0],"recent":[1],"advances":[2],"in":[3,10],"voice":[4,53],"separation":[5,54,75],"methods,":[6],"many":[7],"challenges":[8],"remain":[9],"realistic":[11],"scenarios":[12],"such":[13],"as":[14],"noisy":[15],"recording":[16],"and":[17,33,76,97],"the":[18,31,65,80,85,90,94],"limits":[19],"of":[20,36,68,108],"available":[21],"data.":[22],"In":[23],"this":[24],"work,":[25],"we":[26],"propose":[27],"to":[28,63],"explicitly":[29],"incorporate":[30],"phonetic":[32,69],"linguistic":[34],"nature":[35],"speech":[37,48,74],"by":[38],"taking":[39],"a":[40],"transfer":[41],"learning":[42],"approach":[43],"using":[44],"an":[45,100],"end-to-end":[46],"automatic":[47],"recognition":[49],"(E2EASR)":[50],"system.":[51],"The":[52],"is":[55],"conditioned":[56],"on":[57,73,79],"deep":[58],"features":[59],"extracted":[60],"from":[61],"E2EASR":[62],"cover":[64],"long-term":[66],"dependence":[67],"aspects.":[70],"Experimental":[71],"results":[72],"enhancement":[77],"task":[78],"AVSpeech":[81],"dataset":[82],"show":[83],"that":[84,104],"proposed":[86],"method":[87],"significantly":[88],"improves":[89],"signal-to-distortion":[91],"ratio":[92],"over":[93],"baseline":[95],"model":[96],"even":[98],"outperforms":[99],"audio":[101],"visual":[102,106],"model,":[103],"utilizes":[105],"information":[107],"lip":[109],"movements.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}