{"id":"https://openalex.org/W101846413","doi":"https://doi.org/10.21437/interspeech.2007-485","title":"Using a small development set to build a robust dialectal Chinese speech recognizer","display_name":"Using a small development set to build a robust dialectal Chinese speech recognizer","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W101846413","doi":"https://doi.org/10.21437/interspeech.2007-485","mag":"101846413"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-485","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-485","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","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/A5030700843","display_name":"Linquan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linquan Liu","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084318285","display_name":"Thomas Fang Zheng","orcid":"https://orcid.org/0000-0002-0249-4767"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Thomas Fang Zheng","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068769269","display_name":"Makoto Akabane","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Makoto Akabane","raw_affiliation_strings":["Sony"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081135618","display_name":"Ruxin Chen","orcid":"https://orcid.org/0009-0000-0624-4127"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruxin Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082058381","display_name":"Wenhu Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhu Wu","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1729","last_page":"1732"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9965999722480774,"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/T10860","display_name":"Speech and Audio Processing","score":0.9934999942779541,"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/pronunciation","display_name":"Pronunciation","score":0.886300802230835},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7656508684158325},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7423607707023621},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.5561425089836121},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5186507105827332},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5046266317367554},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.46680358052253723},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43915510177612305},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.43688878417015076},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4336645305156708},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.4301793873310089},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3844728469848633},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3434675335884094},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15377476811408997}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.886300802230835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7656508684158325},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7423607707023621},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.5561425089836121},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5186507105827332},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5046266317367554},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.46680358052253723},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43915510177612305},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.43688878417015076},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4336645305156708},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.4301793873310089},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3844728469848633},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3434675335884094},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15377476811408997},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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":2,"locations":[{"id":"doi:10.21437/interspeech.2007-485","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-485","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.528.6667","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.528.6667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cslt.riit.tsinghua.edu.cn/~fzheng/PAPERS/2007/0708E_EuroSpeech_Using-Small-DevData-for-DCASR_LLQ(ZF).pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W5524598","https://openalex.org/W167428729","https://openalex.org/W1495628564","https://openalex.org/W1555197703","https://openalex.org/W1593915653","https://openalex.org/W1992155534","https://openalex.org/W1996545497","https://openalex.org/W2076960297","https://openalex.org/W2130806807","https://openalex.org/W2139600619","https://openalex.org/W2169883442"],"related_works":["https://openalex.org/W2061937230","https://openalex.org/W2132658536","https://openalex.org/W3081187864","https://openalex.org/W4380605396","https://openalex.org/W2803306015","https://openalex.org/W3133352777","https://openalex.org/W2008737763","https://openalex.org/W151018310","https://openalex.org/W2784059283","https://openalex.org/W4319779560"],"abstract_inverted_index":{"To":[0],"make":[1],"full":[2],"use":[3],"of":[4,50,58,63,108,161],"a":[5,12,19,29,48,56,85,92,101],"small":[6,86],"development":[7],"data":[8,89,96],"set":[9],"to":[10,70],"build":[11],"robust":[13],"dialectal":[14,59,87,112,170],"Chinese":[15,21,26,88,95,113],"speech":[16,22,172],"recognizer":[17,23],"from":[18],"standard":[20,51,120],"(based":[24],"on":[25,84],"Initial/Final,":[27],"IF),":[28],"novel,":[30],"simple":[31],"but":[32],"effective":[33],"acoustic":[34,178],"modeling":[35,80,179],"method,":[36],"named":[37],"state-dependent":[38],"phoneme-based":[39],"model":[40],"merging":[41],"(SDPBMM),":[42],"is":[43,53,81,151],"proposed":[44,82],"and":[45,134,146],"evaluated,":[46],"where":[47],"shared-state":[49],"tri-IF":[52],"merged":[54],"with":[55,72,114,139,153],"state":[57],"mono-IF":[60],"in":[61,68,76],"terms":[62],"pronunciation":[64,74,79,176],"variation":[65],"modeling.":[66],"Specifically,":[67],"order":[69],"deal":[71],"phonetic-level":[73],"variations":[75],"SDPBMM,":[77],"distance-based":[78],"based":[83],"set.":[90],"With":[91],"40-minute":[93],"Shanghai-dialectal":[94],"set,":[97],"SDPBMM":[98,123,150],"can":[99,124,164],"achieve":[100],"significant":[102],"syllable":[103],"error":[104],"rate":[105],"(SER)":[106],"reduction":[107,160],"14.3":[109],"%":[110,145,163],"for":[111,119],"almost":[115],"no":[116],"performance":[117],"degradation":[118],"Chinese.":[121],"Experimentally,":[122],"also":[125],"outperform":[126],"the":[127,135,154],"maximum":[128],"likelihood":[129],"linear":[130],"regression":[131],"(MLLR)":[132],"adaptation":[133],"pooled":[136],"retraining":[137],"methods":[138],"relative":[140,158],"SER":[141,159],"reductions":[142],"by":[143],"2.8":[144],"10.6%,":[147],"respectively.":[148],"If":[149],"combined":[152],"MLLR":[155],"adaptation,":[156],"another":[157],"3.3":[162],"be":[165],"further":[166],"achieved.":[167],"Index":[168],"Terms:":[169],"Chinese,":[171],"recognition,":[173],"accented":[174],"speech,":[175],"modeling,":[177]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}