{"id":"https://openalex.org/W2148194157","doi":"https://doi.org/10.1109/fskd.2012.6234022","title":"Improved acoustic models for Conversational Telephone Speech recognition","display_name":"Improved acoustic models for Conversational Telephone Speech recognition","publication_year":2012,"publication_date":"2012-05-01","ids":{"openalex":"https://openalex.org/W2148194157","doi":"https://doi.org/10.1109/fskd.2012.6234022","mag":"2148194157"},"language":"en","primary_location":{"id":"doi:10.1109/fskd.2012.6234022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2012.6234022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 9th International Conference on Fuzzy Systems and Knowledge Discovery","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/A5100375544","display_name":"Qingqing Zhang","orcid":"https://orcid.org/0000-0002-5507-466X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qingqing Zhang","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000136889","display_name":"Shang Cai","orcid":"https://orcid.org/0000-0002-0230-0440"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shang Cai","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111847664","display_name":"Jielin Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jielin Pan","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100425112","display_name":"Yonghong Yan","orcid":"https://orcid.org/0000-0001-6907-5770"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Yan","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100375544"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13445473,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"1229","last_page":"1232"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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":0.9962999820709229,"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":0.802904486656189},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7748348712921143},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.6705360412597656},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6227078437805176},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6153287291526794},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5839303731918335},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5290816426277161},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5148231387138367},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.4693794250488281},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.44353923201560974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4135546386241913},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.325833261013031},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.26039499044418335}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.802904486656189},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7748348712921143},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.6705360412597656},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6227078437805176},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6153287291526794},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5839303731918335},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5290816426277161},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5148231387138367},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.4693794250488281},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.44353923201560974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4135546386241913},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.325833261013031},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26039499044418335},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fskd.2012.6234022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2012.6234022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 9th International Conference on Fuzzy Systems and Knowledge Discovery","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6399999856948853,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W29925427","https://openalex.org/W1493817255","https://openalex.org/W2021502523","https://openalex.org/W2047497400","https://openalex.org/W2096860695","https://openalex.org/W2105830342","https://openalex.org/W2106119541","https://openalex.org/W2108060348","https://openalex.org/W2115585811","https://openalex.org/W2125436743","https://openalex.org/W2125610823","https://openalex.org/W2136711599","https://openalex.org/W2150907703","https://openalex.org/W2153682659","https://openalex.org/W2167535584"],"related_works":["https://openalex.org/W2145230572","https://openalex.org/W2166312020","https://openalex.org/W3081187864","https://openalex.org/W4380605396","https://openalex.org/W2803306015","https://openalex.org/W4401751953","https://openalex.org/W3133352777","https://openalex.org/W156567445","https://openalex.org/W3136989387","https://openalex.org/W151018310"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"advances":[3],"for":[4],"acoustic":[5,24,66,83,98],"models":[6,67,84,99],"in":[7,22,51,55],"Chinese":[8],"spontaneous":[9],"Conversational":[10],"Telephone":[11],"Speech":[12],"(CTS)":[13],"recognition":[14,56],"task.":[15],"A":[16],"number":[17],"of":[18,74],"approaches":[19],"were":[20,58,68],"investigated":[21],"the":[23,62,86,96],"modeling,":[25],"including":[26],"Heteroscedastic":[27],"Linear":[28],"Discriminant":[29],"Analysis":[30],"(HLDA),":[31],"Vocal":[32],"Tract":[33],"Length":[34],"Normalization":[35],"(VTLN),":[36],"Gaussianization,":[37],"Minimum":[38],"Phone":[39],"Error":[40,89],"(MPE),":[41],"Feature":[42],"space":[43],"MPE":[44],"(fMPE),":[45],"and":[46,105],"etc.":[47],"Considering":[48],"pronunciation":[49],"variations":[50],"continuous":[52],"speech,":[53],"tones":[54],"vocabulary":[57],"modified":[59],"due":[60],"to":[61],"Sandhi":[63],"rule.":[64],"The":[65,81],"trained":[69],"on":[70,100],"over":[71,95],"200":[72],"hours":[73],"audio":[75],"data":[76,110],"from":[77],"standard":[78,101],"LDC":[79,102],"corpora.":[80],"improved":[82],"reduce":[85],"relative":[87],"Character":[88],"Rate":[90],"(CER)":[91],"by":[92],"about":[93],"25%":[94],"baseline":[97],"test":[103],"set":[104],"China":[106],"863":[107],"program":[108],"evaluation":[109],"set.":[111]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}