{"id":"https://openalex.org/W4225632569","doi":"https://doi.org/10.21437/interspeech.2022-10706","title":"Leveraging Real Conversational Data for Multi-Channel Continuous Speech Separation","display_name":"Leveraging Real Conversational Data for Multi-Channel Continuous Speech Separation","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4225632569","doi":"https://doi.org/10.21437/interspeech.2022-10706"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10706","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10706","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5005333910","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0000-0002-8482-6138"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaofei Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100408281","display_name":"Dongmei Wang","orcid":"https://orcid.org/0000-0002-6930-0066"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongmei Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016279564","display_name":"Naoyuki Kanda","orcid":"https://orcid.org/0000-0002-8628-3288"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naoyuki Kanda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026088950","display_name":"\u015eefik Emre Eskimez","orcid":"https://orcid.org/0000-0001-6259-5925"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sefik Emre Eskimez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","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":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3814","last_page":"3818"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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/T11309","display_name":"Music and Audio Processing","score":0.98580002784729,"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/computer-science","display_name":"Computer science","score":0.7748636603355408},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6355531811714172},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5555583834648132},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4735547602176666},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42331019043922424},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3277307152748108},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.15547865629196167},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07899576425552368}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7748636603355408},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6355531811714172},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5555583834648132},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4735547602176666},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42331019043922424},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3277307152748108},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.15547865629196167},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07899576425552368}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10706","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10706","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W2106462793","https://openalex.org/W2559837139","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2099105119","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Existing":[0],"multi-channel":[1,133],"continuous":[2,96],"speech":[3],"separation":[4],"(CSS)":[5],"models":[6],"are":[7,144],"heavily":[8],"dependent":[9],"on":[10,115,147],"supervised":[11,64],"data":[12,16,19,65,85,91,113,134,152,180],"-":[13],"either":[14],"simulated":[15,84],"which":[17,33,103,129],"causes":[18],"mismatch":[20],"between":[21,99],"the":[22,28,43,57,100,104,116,132,154,169,172],"training":[23,54,79,88,98,163],"and":[24,66,86,93,153],"real-data":[25],"testing,":[26],"or":[27],"real":[29,112,178],"transcribed":[30,90],"overlapping":[31],"data,":[32],"is":[34,107],"difficult":[35],"to":[36,124],"be":[37],"acquired,":[38],"hindering":[39],"further":[40,108],"improvements":[41],"in":[42,102],"conversational/meeting":[44],"transcription":[45,142],"tasks.":[46],"In":[47],"this":[48,122],"paper,":[49],"we":[50],"propose":[51],"a":[52,94],"three-stage":[53],"scheme":[55,74,123],"for":[56,181],"CSS":[58,105,127,182],"model":[59,106,183],"that":[60,175],"can":[61,130],"leverage":[62],"both":[63,148],"extra":[67],"large-scale":[68],"unsupervised":[69],"real-world":[70],"conversational":[71,179],"data.":[72],"The":[73,158],"consists":[75],"of":[76,171],"two":[77],"conventional":[78],"approaches":[80],"--":[81,92],"pre-training":[82],"using":[83,89,111],"ASR-loss-based":[87],"novel":[95],"semi-supervised":[97],"two,":[101],"trained":[109],"by":[110,161],"based":[114],"teacher-student":[117],"learning":[118],"framework.":[119],"We":[120],"apply":[121],"an":[125],"array-geometry-agnostic":[126],"model,":[128],"use":[131],"collected":[135],"from":[136],"any":[137],"microphone":[138],"array.":[139],"Large-scale":[140],"meeting":[141,151,156],"experiments":[143],"carried":[145],"out":[146],"Microsoft":[149],"internal":[150],"AMI":[155],"corpus.":[157],"steady":[159],"improvement":[160],"each":[162],"stage":[164],"has":[165],"been":[166],"observed,":[167],"showing":[168],"effect":[170],"proposed":[173],"method":[174],"enables":[176],"leveraging":[177],"training.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}