{"id":"https://openalex.org/W48790062","doi":"https://doi.org/10.21437/interspeech.2004-17","title":"Acoustic model adaptation for coded speech using synthetic speech","display_name":"Acoustic model adaptation for coded speech using synthetic speech","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W48790062","doi":"https://doi.org/10.21437/interspeech.2004-17","mag":"48790062"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-17","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-17","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5002528469","display_name":"Koji Tanaka","orcid":"https://orcid.org/0000-0003-4747-3457"},"institutions":[{"id":"https://openalex.org/I922474255","display_name":"Tokushima University","ror":"https://ror.org/044vy1d05","country_code":"JP","type":"education","lineage":["https://openalex.org/I922474255"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koji Tanaka","raw_affiliation_strings":["Univ. of Tokushima"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Tokushima","institution_ids":["https://openalex.org/I922474255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071943346","display_name":"Fuji Ren","orcid":"https://orcid.org/0000-0003-4860-9184"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fuji Ren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112035972","display_name":"Shingo Kuroiwa","orcid":null},"institutions":[{"id":"https://openalex.org/I922474255","display_name":"Tokushima University","ror":"https://ror.org/044vy1d05","country_code":"JP","type":"education","lineage":["https://openalex.org/I922474255"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shingo Kuroiwa","raw_affiliation_strings":["Univ. of Tokushima"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Tokushima","institution_ids":["https://openalex.org/I922474255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113866096","display_name":"Satoru Tsuge","orcid":"https://orcid.org/0000-0002-3392-7852"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Satoru Tsuge","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00319577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2925","last_page":"2928"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9927999973297119,"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/T11309","display_name":"Music and Audio Processing","score":0.9915000200271606,"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":0.8361092805862427},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8077881336212158},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7030607461929321},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6852819919586182},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.6244422793388367},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.614576518535614},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5512619018554688},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5017833709716797},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.44536203145980835},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41200560331344604},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3629143238067627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30537155270576477},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06222531199455261}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8361092805862427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8077881336212158},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7030607461929321},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6852819919586182},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.6244422793388367},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.614576518535614},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5512619018554688},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5017833709716797},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.44536203145980835},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41200560331344604},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3629143238067627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30537155270576477},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06222531199455261},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-17","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-17","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W111357272","https://openalex.org/W1965255698","https://openalex.org/W2096980176","https://openalex.org/W2100969003","https://openalex.org/W2131711534","https://openalex.org/W2146871184","https://openalex.org/W2154920538"],"related_works":["https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W1546240199","https://openalex.org/W193702574","https://openalex.org/W2121652828","https://openalex.org/W642007152"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"describe":[4],"a":[5,68],"novel":[6],"acoustic":[7,87],"model":[8,55,88],"adaptation":[9,64,72,83],"technique":[10],"which":[11],"generates":[12],"\u201cspeaker-independent\u201d":[13],"HMM":[14],"for":[15,35,101],"the":[16,41,62,86,112],"target":[17],"environment.":[18],"Recently,":[19],"personal":[20],"digital":[21],"assistants":[22],"like":[23],"cellular":[24],"phones":[25],"are":[26],"shifting":[27],"to":[28,81],"IP":[29,38],"terminals.":[30],"The":[31,74],"encoding-decoding":[32],"process":[33],"utilized":[34],"transmitting":[36],"over":[37],"networks":[39],"deteriorates":[40],"quality":[42],"of":[43,71,89,125],"speech":[44,51,79,91,99,108,116],"data.":[45,73],"This":[46],"deterioration":[47],"causes":[48],"degradation":[49],"in":[50],"recognition":[52,59,109,117],"performance.":[53,60,118],"Acoustic":[54],"adaptations":[56],"can":[57],"improve":[58],"However,":[61],"conventional":[63],"methods":[65],"usually":[66],"require":[67,97],"large":[69],"amount":[70],"proposed":[75,113],"method":[76,114],"uses":[77],"HMM-based":[78,90],"synthesis":[80],"generate":[82],"data":[84,100],"from":[85],"recognizer,":[92],"and":[93],"consequently":[94],"does":[95],"not":[96],"any":[98],"adaptation.":[102],"Experimental":[103],"results":[104],"on":[105],"G.723.1":[106],"coded":[107],"show":[110],"that":[111],"improves":[115],"A":[119],"relative":[120],"word":[121],"error":[122],"rate":[123],"reduction":[124],"approximately":[126],"12%":[127],"was":[128],"observed.":[129]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}