{"id":"https://openalex.org/W4402111241","doi":"https://doi.org/10.21437/interspeech.2024-1264","title":"Transcription-Free Fine-Tuning of Speech Separation Models for Noisy and Reverberant Multi-Speaker Automatic Speech Recognition","display_name":"Transcription-Free Fine-Tuning of Speech Separation Models for Noisy and Reverberant Multi-Speaker Automatic Speech Recognition","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111241","doi":"https://doi.org/10.21437/interspeech.2024-1264"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1264","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1264","pdf_url":"https://www.isca-archive.org/interspeech_2024/ravenscroft24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2024/ravenscroft24_interspeech.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004802529","display_name":"William Ravenscroft","orcid":"https://orcid.org/0000-0002-0780-3303"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"William Ravenscroft","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012132420","display_name":"George Close","orcid":"https://orcid.org/0000-0002-9478-5421"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Close","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027797344","display_name":"Stefan Goetze","orcid":"https://orcid.org/0000-0003-1044-7343"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefan Goetze","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030528300","display_name":"Thomas Hain","orcid":"https://orcid.org/0000-0003-0939-3464"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Hain","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064273942","display_name":"Mohammad Soleymanpour","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammad Soleymanpour","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086353379","display_name":"Anurag Chowdhury","orcid":"https://orcid.org/0000-0001-8758-988X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anurag Chowdhury","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005148508","display_name":"Mark C. Fuhs","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark C. Fuhs","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5004802529"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9948,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80142062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4998","last_page":"5002"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9832000136375427,"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":0.9832000136375427,"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":0.9603999853134155,"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/speech-recognition","display_name":"Speech recognition","score":0.8187004327774048},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7508081793785095},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.573068380355835},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.556814968585968},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5442443490028381},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5366866588592529},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.44065964221954346},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.42511457204818726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34972506761550903}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8187004327774048},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7508081793785095},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.573068380355835},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.556814968585968},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5442443490028381},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5366866588592529},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.44065964221954346},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.42511457204818726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34972506761550903},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-1264","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1264","pdf_url":"https://www.isca-archive.org/interspeech_2024/ravenscroft24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2024-1264","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1264","pdf_url":"https://www.isca-archive.org/interspeech_2024/ravenscroft24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2831959038","display_name":null,"funder_award_id":"EP/S023062","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"},{"id":"https://openalex.org/G5306878388","display_name":null,"funder_award_id":"EP/S023062/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402111241.pdf","grobid_xml":"https://content.openalex.org/works/W4402111241.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W642007152","https://openalex.org/W2154415461","https://openalex.org/W2056066842"],"abstract_inverted_index":{"One":[0],"solution":[1],"to":[2,11,37,91],"automatic":[3],"speech":[4,13],"recognition":[5],"(ASR)":[6],"of":[7,80],"overlapping":[8],"speakers":[9],"is":[10,45,59],"separate":[12],"and":[14,42,115],"then":[15],"perform":[16],"ASR":[17,29,43,82],"on":[18,51],"the":[19,22,40],"separated":[20],"signals.Commonly,":[21],"separator":[23],"produces":[24],"artefacts":[25],"which":[26],"often":[27,46],"degrade":[28],"performance.Addressing":[30],"this":[31],"issue":[32],"typically":[33],"requires":[34],"reference":[35,56],"transcriptions":[36],"jointly":[38],"train":[39],"separation":[41],"networks.This":[44],"not":[47,60],"viable":[48],"for":[49,68],"training":[50,70,94],"real-world":[52],"in-domain":[53],"audio":[54,73],"where":[55],"transcript":[57],"information":[58],"always":[61],"available.This":[62],"paper":[63],"proposes":[64],"a":[65,85,88,102,112],"transcription-free":[66],"method":[67,76,100],"joint":[69],"using":[71],"only":[72],"signals.The":[74],"proposed":[75,89],"uses":[77],"embedding":[78],"differences":[79],"pre-trained":[81],"encoders":[83],"as":[84,124],"loss":[86,114],"with":[87],"modification":[90],"permutation":[92],"invariant":[93],"(PIT)":[95],"called":[96],"guided":[97],"PIT":[98],"(GPIT).The":[99],"achieves":[101],"6.4%":[103],"improvement":[104],"in":[105,120],"word":[106],"error":[107],"rate":[108],"(WER)":[109],"measures":[110,122],"over":[111],"signal-level":[113],"also":[116],"shows":[117],"enhancement":[118],"improvements":[119],"perceptual":[121],"such":[123],"short-time":[125],"objective":[126],"intelligibility":[127],"(STOI).":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}