{"id":"https://openalex.org/W157326083","doi":"https://doi.org/10.21437/interspeech.2004-24","title":"Methods for task adaptation of acoustic models with limited transcribed in-domain data","display_name":"Methods for task adaptation of acoustic models with limited transcribed in-domain data","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W157326083","doi":"https://doi.org/10.21437/interspeech.2004-24","mag":"157326083"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-24","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-24","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":"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/A5053566853","display_name":"Enrico Bocchieri","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Enrico Bocchieri","raw_affiliation_strings":["At&T#TAB#"],"affiliations":[{"raw_affiliation_string":"At&T#TAB#","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014137885","display_name":"Michael Riley","orcid":"https://orcid.org/0009-0002-9449-025X"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Riley","raw_affiliation_strings":["At&T#TAB#"],"affiliations":[{"raw_affiliation_string":"At&T#TAB#","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055086464","display_name":"Murat Sara\u00e7lar","orcid":"https://orcid.org/0000-0002-7435-8510"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Murat Saraclar","raw_affiliation_strings":["Google\u2020#TAB#"],"affiliations":[{"raw_affiliation_string":"Google\u2020#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053566853"],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":0.4625,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73186648,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2953","last_page":"2956"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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":0.8134630918502808},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6318982839584351},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5978183746337891},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5798386335372925},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5689738988876343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4683994948863983},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.458954393863678},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.454642653465271},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4258001446723938},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.42501574754714966},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.39484748244285583},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.366972953081131},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0831938087940216}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8134630918502808},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6318982839584351},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5978183746337891},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5798386335372925},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5689738988876343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4683994948863983},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.458954393863678},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.454642653465271},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4258001446723938},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.42501574754714966},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.39484748244285583},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.366972953081131},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0831938087940216},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2004-24","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-24","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.418.8895","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.418.8895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://busim.ee.boun.edu.tr/~murat/publications/icslp04.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1596641231","https://openalex.org/W2035514778","https://openalex.org/W2097048430","https://openalex.org/W2100969003","https://openalex.org/W2115900267","https://openalex.org/W2136711599","https://openalex.org/W2143577772","https://openalex.org/W2146871184","https://openalex.org/W2158069733","https://openalex.org/W2171761326","https://openalex.org/W2276283915","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2526843974","https://openalex.org/W2749784707","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W642007152","https://openalex.org/W2122233706","https://openalex.org/W2105439218","https://openalex.org/W3143423642","https://openalex.org/W2131711534","https://openalex.org/W2341426843"],"abstract_inverted_index":{"Application":[0],"specific":[1],"acoustic":[2,35,66],"models":[3,67,84],"provide":[4],"the":[5,16,34,63,69,95,101,150,158,177],"best":[6],"recognition":[7],"accuracy,":[8],"but":[9],"they":[10,14],"are":[11],"expensive,":[12],"because":[13],"require":[15],"transcription":[17],"of":[18,22,24,47,58,65,97,119,132,142,174,179],"tens":[19],"or":[20],"hundreds":[21],"hours":[23,141,173],"in-domain":[25,40,71,83,102,126,136,143,175],"speech":[26,42,72,144],"for":[27,145],"training.":[28],"Therefore,":[29],"this":[30,169],"paper":[31],"focuses":[32],"on":[33,68,124],"model":[36,146],"estimation":[37],"given":[38],"limited":[39,70],"transcribed":[41,50],"data,":[43],"and":[44,88,128,163],"large":[45],"amounts":[46],"(typically":[48],"available)":[49],"out-of-domain":[51,86],"data.":[52,73,103],"First,":[53],"we":[54,75,110,148],"evaluate":[55],"several":[56],"combinations":[57],"known":[59],"methods":[60,113],"to":[61,77,81,93,168,183],"optimize":[62],"adaptation/training":[64],"Then,":[74],"propose":[76],"use":[78],"Gaussian":[79,164],"sharing":[80,165],"combine":[82],"with":[85],"models,":[87],"a":[89,105,129],"data":[90,161],"generation":[91,162],"process":[92],"simulate":[94],"presence":[96],"more":[98],"speakers":[99],"in":[100],"In":[104],"spoken":[106],"language":[107],"dialog":[108],"application,":[109],"contrast":[111],"our":[112],"against":[114],"an":[115],"upper":[116],"accuracy":[117,151,180],"bound":[118,131],"69.1":[120],"%":[121,134,154],"(model":[122],"trained":[123],"many":[125],"data)":[127],"lower":[130,159],"60.8":[133],"(no":[135],"data).":[137],"Using":[138],"only":[139],"2":[140],"estimation,":[147],"improve":[149],"by":[152],"5.1":[153],"(to":[155],"65.9%)":[156],"over":[157],"bound;":[160],"contibute":[166],"2.2%":[167],"improvement.":[170],"With":[171],"9":[172],"speech,":[176],"improvement":[178],"is":[181],"6.5%,":[182],"67.3%.":[184],"1.":[185]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}