{"id":"https://openalex.org/W4297841674","doi":"https://doi.org/10.21437/interspeech.2022-11267","title":"Speaker conditioned acoustic modeling for multi-speaker conversational ASR","display_name":"Speaker conditioned acoustic modeling for multi-speaker conversational ASR","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841674","doi":"https://doi.org/10.21437/interspeech.2022-11267"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11267","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11267","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":"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/A5004929413","display_name":"Srikanth Raj Chetupalli","orcid":"https://orcid.org/0000-0002-2186-5420"},"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":"Srikanth Raj Chetupalli","raw_affiliation_strings":["LEAP lab, Electrical Engineering, Indian Institute of Science, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"LEAP lab, Electrical Engineering, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","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":true,"raw_author_name":"Sriram Ganapathy","raw_affiliation_strings":["LEAP lab, Electrical Engineering, Indian Institute of Science, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"LEAP lab, Electrical Engineering, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002536077"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.3116,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.5088343,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3834","last_page":"3838"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9810000061988831,"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":0.9810000061988831,"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":0.9402999877929688,"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":0.7461563348770142},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7216686606407166},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5542843341827393},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5369939804077148}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7461563348770142},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7216686606407166},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5542843341827393},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5369939804077148}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-11267","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11267","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2046932483","https://openalex.org/W2396230943","https://openalex.org/W2405137844","https://openalex.org/W2734774145","https://openalex.org/W2942544643","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2963266252","https://openalex.org/W2963477857","https://openalex.org/W2963773971","https://openalex.org/W2972949456","https://openalex.org/W2973064719","https://openalex.org/W2973127116","https://openalex.org/W3008357631","https://openalex.org/W3020336359","https://openalex.org/W3032969657","https://openalex.org/W3095212884","https://openalex.org/W3097643313","https://openalex.org/W3143843080","https://openalex.org/W3153518906","https://openalex.org/W3198248809","https://openalex.org/W4225585130","https://openalex.org/W4287632494","https://openalex.org/W4295312788"],"related_works":["https://openalex.org/W2162158162","https://openalex.org/W1521049138","https://openalex.org/W1509309911","https://openalex.org/W2144208207","https://openalex.org/W2175373321","https://openalex.org/W2499802997","https://openalex.org/W1497807607","https://openalex.org/W1813780412","https://openalex.org/W2128773298","https://openalex.org/W2312116756"],"abstract_inverted_index":{"In":[0],"this":[1,93],"paper,":[2],"we":[3,95,146],"propose":[4],"a":[5,26,29,34,52],"novel":[6],"approach":[7,112],"for":[8,83,87],"the":[9,47,59,64,74,85,91,98,117,121,132,138,149,163,180],"transcription":[10],"of":[11,28,51,54,73,141,172],"speech":[12,21,37],"conversations":[13],"with":[14,97,166],"natural":[15],"speaker":[16,30,41,60,69,77,89,100,107,135,154],"overlap,":[17],"from":[18,63,137],"single":[19],"channel":[20],"recordings.The":[22],"proposed":[23,115,150],"model":[24,44,119,124],"is":[25,113],"combination":[27],"diarization":[31,65,108,118],"system":[32,49,66,165],"and":[33,120,157],"hybrid":[35],"automatic":[36,99],"recognition":[38],"(ASR)":[39],"system.The":[40],"conditioned":[42],"acoustic":[43,123,151],"(SCAM)":[45],"in":[46,90,174],"ASR":[48,122,164],"consists":[50],"series":[53],"embedding":[55],"layers":[56],"which":[57],"use":[58],"activity":[61,101,155],"inputs":[62],"to":[67],"derive":[68],"specific":[70,78],"embeddings.The":[71],"output":[72],"SCAM":[75],"are":[76,81,125,129],"senones":[79],"that":[80,148],"used":[82],"decoding":[84],"transcripts":[86],"each":[88],"conversation.In":[92],"work,":[94],"experiment":[96],"decisions":[102,156],"generated":[103],"using":[104],"an":[105],"endto-end":[106],"system.A":[109],"joint":[110,158],"learning":[111],"also":[114],"where":[116],"jointly":[126],"optimized.The":[127],"experiments":[128],"performed":[130],"on":[131],"mixed-channel":[133],"two":[134],"recordings":[136],"Switchboard":[139],"corpus":[140],"telephone":[142],"conversations.In":[143],"these":[144],"experiments,":[145],"show":[147],"model,":[152],"incorporating":[153],"optimization,":[159],"improves":[160],"significantly":[161],"over":[162,179],"explicit":[167],"source":[168],"filtering":[169],"(relative":[170],"improvements":[171],"12%":[173],"word":[175],"error":[176],"rate":[177],"(WER)":[178],"baseline":[181],"system).":[182]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}