{"id":"https://openalex.org/W3198522318","doi":"https://doi.org/10.21437/interspeech.2021-2155","title":"Multi-Speaker ASR Combining Non-Autoregressive Conformer CTC and Conditional Speaker Chain","display_name":"Multi-Speaker ASR Combining Non-Autoregressive Conformer CTC and Conditional Speaker Chain","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198522318","doi":"https://doi.org/10.21437/interspeech.2021-2155","mag":"3198522318"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-2155","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2155","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101783173","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0009-0001-2388-5935"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengcheng Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuankai Chang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9049,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.88742383,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3720","last_page":"3724"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.98089998960495,"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":0.9714999794960022,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.79374760389328},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7150757312774658},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6607485413551331},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6500297784805298},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6286572217941284},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6116834878921509},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4815285801887512},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4197341203689575},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4062821567058563},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.30935657024383545},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17221292853355408},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11002808809280396}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.79374760389328},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7150757312774658},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6607485413551331},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6500297784805298},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6286572217941284},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6116834878921509},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4815285801887512},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4197341203689575},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4062821567058563},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30935657024383545},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17221292853355408},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11002808809280396},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-2155","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2155","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2171218219","https://openalex.org/W1972271943","https://openalex.org/W2150410159","https://openalex.org/W4327525404","https://openalex.org/W4287185323","https://openalex.org/W3150905897","https://openalex.org/W1520183331","https://openalex.org/W2734842993","https://openalex.org/W3128807919","https://openalex.org/W3176411177"],"abstract_inverted_index":{"Non-autoregressive":[0],"(NAR)":[1],"models":[2,16,141],"have":[3],"achieved":[4],"a":[5,83,144],"large":[6],"inference":[7,101],"computation":[8],"reduction":[9],"and":[10,75,118,131,153,184,188],"comparable":[11],"results":[12],"with":[13,142,176],"autoregressive":[14],"(AR)":[15],"on":[17,35,129,186],"various":[18],"sequence":[19,21,36],"to":[20,30,37,56,92,106,124],"tasks.":[22],"However,":[23],"there":[24],"has":[25],"been":[26],"limited":[27],"research":[28],"aiming":[29],"explore":[31],"the":[32,61,71,99,107,116,126,159,172],"NAR":[33,57,84,140],"approaches":[34],"multi-sequence":[38],"problems,":[39],"like":[40],"multi-speaker":[41,58],"automatic":[42],"speech":[43,74],"recognition":[44],"(ASR).":[45],"In":[46,80],"this":[47,97,199],"study,":[48],"we":[49,113],"extend":[50],"our":[51,136,166,193],"proposed":[52],"conditional":[53,77],"chain":[54],"model":[55,137,167,175],"ASR.":[59],"Specifically,":[60],"output":[62],"of":[63,109,147,151,161,164,182,192],"each":[64,81],"speaker":[65,78],"is":[66,90],"inferred":[67],"one-by-one":[68],"using":[69],"both":[70],"input":[72],"mixture":[73],"previously-estimated":[76],"features.":[79],"step,":[82],"connectionist":[85],"temporal":[86],"classification":[87],"(CTC)":[88],"encoder":[89],"used":[91],"perform":[93],"parallel":[94],"computation.":[95],"With":[96],"design,":[98],"total":[100],"steps":[102],"will":[103],"be":[104],"restricted":[105],"number":[108],"mixed":[110],"speakers.":[111],"Besides,":[112],"also":[114],"adopt":[115],"Conformer":[117],"incorporate":[119],"an":[120],"intermediate":[121],"CTC":[122],"loss":[123],"improve":[125],"performance.":[127],"Experiments":[128],"WSJ0-Mix":[130],"LibriMix":[132],"corpora":[133],"show":[134],"that":[135],"outperforms":[138],"other":[139],"only":[143,177],"slight":[145],"increase":[146],"latency,":[148,179],"achieving":[149],"WERs":[150,181],"22.3%":[152],"24.9%,":[154],"respectively.":[155],"Moreover,":[156],"by":[157],"including":[158],"data":[160],"variable":[162],"numbers":[163],"speakers,":[165],"can":[168],"even":[169],"better":[170],"than":[171],"PIT-Conformer":[173],"AR":[174],"1/7":[178],"obtaining":[180],"19.9%":[183],"34.3%":[185],"WSJ0-2mix":[187],"WSJ0-3mix":[189],"sets.":[190],"All":[191],"codes":[194],"are":[195],"publicly":[196],"available":[197],"at":[198],"https":[200],"URL.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}