{"id":"https://openalex.org/W2099813353","doi":"https://doi.org/10.1109/icassp.1982.1171490","title":"Automatic labeling of speech","display_name":"Automatic labeling of speech","publication_year":2005,"publication_date":"2005-03-24","ids":{"openalex":"https://openalex.org/W2099813353","doi":"https://doi.org/10.1109/icassp.1982.1171490","mag":"2099813353"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.1982.1171490","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1982.1171490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '82. IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5005597610","display_name":"Jim Spohrer","orcid":"https://orcid.org/0000-0002-9864-2735"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"J. Spohrer","raw_affiliation_strings":["Verbex, Bedford, MA, USA"],"affiliations":[{"raw_affiliation_string":"Verbex, Bedford, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087477752","display_name":"Peter Brown","orcid":"https://orcid.org/0000-0002-5201-3044"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"P. Brown","raw_affiliation_strings":["Verbex, Bedford, MA, USA"],"affiliations":[{"raw_affiliation_string":"Verbex, Bedford, MA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102770672","display_name":"Robert Roth","orcid":"https://orcid.org/0000-0003-4991-712X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R. Roth","raw_affiliation_strings":["Verbex, Bedford, MA, USA"],"affiliations":[{"raw_affiliation_string":"Verbex, Bedford, MA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005597610"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4387,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74062994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"7","issue":null,"first_page":"1641","last_page":"1644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9909999966621399,"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":0.9909999966621399,"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":0.9812999963760376,"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/T12031","display_name":"Speech and dialogue systems","score":0.9498000144958496,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8373587131500244},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7482373118400574},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.5544499754905701},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5402244329452515},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5262645483016968},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5222571492195129},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.508188009262085},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49074041843414307},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4639067053794861},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4299035668373108},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.40731891989707947}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8373587131500244},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7482373118400574},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.5544499754905701},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5402244329452515},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5262645483016968},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5222571492195129},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.508188009262085},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49074041843414307},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4639067053794861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4299035668373108},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.40731891989707947},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.1982.1171490","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1982.1171490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '82. IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W1575431606","https://openalex.org/W6634270078"],"related_works":["https://openalex.org/W2184127972","https://openalex.org/W2964829415","https://openalex.org/W3159882232","https://openalex.org/W642007152","https://openalex.org/W4210930959","https://openalex.org/W2131711534","https://openalex.org/W2343205865","https://openalex.org/W2122924390","https://openalex.org/W2550171623","https://openalex.org/W2341426843"],"abstract_inverted_index":{"To":[0],"evaluate":[1],"the":[2,34,63,86,108],"performance":[3],"of":[4,11,65,88,124],"a":[5,26,80,89,93,99,120],"speech":[6,31,36,67],"recognition":[7,90],"system,":[8,91],"large":[9,66],"databases":[10],"labeled":[12,39],"speech,":[13],"including":[14],"various":[15],"speakers,":[16],"noise":[17],"conditions,":[18],"and":[19,45,58,60,92,111],"vocabularies,":[20],"are":[21],"necessary.":[22],"This":[23,54],"paper":[24],"describes":[25],"method":[27,72,115],"for":[28,62],"automatically":[29],"labeling":[30,71,101],"data.":[32],"In":[33],"past,":[35],"has":[37],"been":[38],"manually,":[40],"typically":[41],"by":[42,106],"listening":[43],"to":[44,78,118],"viewing":[46],"waveforms":[47],"through":[48],"real-time,":[49],"interactive":[50],"computer":[51],"I/O":[52],"stations.":[53],"process":[55],"is":[56,83],"slow":[57],"tedious,":[59],"accounts":[61],"shortage":[64],"databases.":[68],"The":[69,96,114],"automatic":[70],"reported":[73],"here":[74],"uses":[75],"dynamic":[76],"programming":[77],"align":[79],"script":[81],"which":[82,102],"produced":[84],"as":[85],"output":[87],"known":[94],"script.":[95],"alignment":[97,112],"gives":[98],"tentative":[100],"can":[103],"be":[104],"refined":[105],"repeating":[107],"training,":[109],"recognition,":[110],"processes.":[113],"was":[116],"used":[117],"label":[119],"50":[121],"speaker":[122],"database":[123],"140,000":[125],"digits.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}