{"id":"https://openalex.org/W7140219204","doi":"https://doi.org/10.1016/j.csl.2026.101984","title":"Scaling multi-speaker speech recognition with high-quality synthetic data","display_name":"Scaling multi-speaker speech recognition with high-quality synthetic data","publication_year":2026,"publication_date":"2026-03-24","ids":{"openalex":"https://openalex.org/W7140219204","doi":"https://doi.org/10.1016/j.csl.2026.101984"},"language":"en","primary_location":{"id":"doi:10.1016/j.csl.2026.101984","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.csl.2026.101984","pdf_url":null,"source":{"id":"https://openalex.org/S91252481","display_name":"Computer Speech & Language","issn_l":"0885-2308","issn":["0885-2308","1095-8363"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Speech &amp; Language","raw_type":"journal-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/A5121016205","display_name":"Shao-Jung Chan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shao-Jung Chan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5047542917","display_name":"Kuang\u2010Yow Lian","orcid":"https://orcid.org/0000-0002-5692-9279"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kuang-Yow Lian","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5692-9279","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5047542917"],"corresponding_institution_ids":[],"apc_list":{"value":3400,"currency":"USD","value_usd":3400},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3036894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"100","issue":null,"first_page":"101984","last_page":"101984"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5109000205993652,"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":0.5109000205993652,"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":0.2354000061750412,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.03970000147819519,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.557699978351593},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4661000072956085},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42899999022483826},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.37880000472068787},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.32670000195503235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8682000041007996},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7026000022888184},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.557699978351593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5044999718666077},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4661000072956085},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42899999022483826},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.319599986076355},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.28139999508857727}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.csl.2026.101984","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.csl.2026.101984","pdf_url":null,"source":{"id":"https://openalex.org/S91252481","display_name":"Computer Speech & Language","issn_l":"0885-2308","issn":["0885-2308","1095-8363"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Speech &amp; Language","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4897799909","display_name":"Ultra-Low Latency and Lightweight Deep Learning Model for Speech Recognition","funder_award_id":"NSTC114-2221-E027-081-MY2","funder_id":"https://openalex.org/F2461203286","funder_display_name":"National Science and Technology Council"}],"funders":[{"id":"https://openalex.org/F2461203286","display_name":"National Science and Technology Council","ror":"https://ror.org/02kv4zf79"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2016589492","https://openalex.org/W3017474798"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2026-03-25T00:00:00"}
