{"id":"https://openalex.org/W2594951208","doi":"https://doi.org/10.1109/iscslp.2016.7918442","title":"Exploiting language-mismatched phoneme recognizers for unsupervised acoustic modeling","display_name":"Exploiting language-mismatched phoneme recognizers for unsupervised acoustic modeling","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2594951208","doi":"https://doi.org/10.1109/iscslp.2016.7918442","mag":"2594951208"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2016.7918442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5053373302","display_name":"Siyuan Feng","orcid":"https://orcid.org/0000-0003-2531-8480"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Siyuan Feng","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001795601","display_name":"Tan Lee","orcid":"https://orcid.org/0000-0002-7089-3436"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tan Lee","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100405764","display_name":"Haipeng Wang","orcid":"https://orcid.org/0009-0009-9392-8505"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haipeng Wang","raw_affiliation_strings":["Noah's Ark Lab, Huawei Technologies Co. Ltd, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Noah's Ark Lab, Huawei Technologies Co. Ltd, Hong Kong","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3249,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.88294862,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"1","last_page":"5"},"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":0.9993000030517578,"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":0.9983000159263611,"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":0.8583371639251709},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7272363901138306},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6432194113731384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5947903394699097},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5843952894210815},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5551856160163879},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4969504177570343},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4889906644821167},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45241615176200867},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41077637672424316},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40938544273376465}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8583371639251709},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7272363901138306},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6432194113731384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5947903394699097},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5843952894210815},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5551856160163879},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4969504177570343},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4889906644821167},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45241615176200867},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41077637672424316},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40938544273376465},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2016.7918442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8199999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W185189022","https://openalex.org/W1578200545","https://openalex.org/W1957665339","https://openalex.org/W1967924372","https://openalex.org/W1975728937","https://openalex.org/W2055408826","https://openalex.org/W2100768664","https://openalex.org/W2106284094","https://openalex.org/W2519200395","https://openalex.org/W4213009331"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W2004087835","https://openalex.org/W2314871050"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"an":[3,37],"investigation":[4],"on":[5,114],"acoustic":[6],"modeling":[7],"in":[8,86],"the":[9,58,70,87,120,123],"absence":[10],"of":[11,29,76,82,108,122],"transcribed":[12],"training":[13],"data.":[14],"We":[15],"propose":[16],"to":[17,22,68,105],"use":[18],"language-mismatched":[19,35],"phoneme":[20,59],"recognizers":[21,93],"assist":[23],"unsupervised":[24],"segmentation":[25,109],"and":[26,110],"segment":[27,47],"clustering":[28,64],"a":[30,34,51,73,80,97,115],"new":[31],"language.":[32,89],"Using":[33],"recognizer,":[36],"input":[38],"utterance":[39],"is":[40,48,55,66],"divided":[41],"into":[42,72],"many":[43],"variable-length":[44],"segments.":[45],"Each":[46],"represented":[49],"by":[50],"feature":[52],"vector":[53],"that":[54],"derived":[56],"from":[57],"posterior":[60],"probabilities.":[61],"A":[62],"spectral":[63],"algorithm":[65],"developed":[67],"group":[69],"segments":[71],"prescribed":[74],"number":[75],"clusters,":[77],"which":[78],"represent":[79],"set":[81],"basic":[83],"speech":[84,117],"units":[85],"target":[88],"By":[90],"exploiting":[91],"multiple":[92],"for":[94],"different":[95],"languages,":[96],"wider":[98],"phonetic":[99],"space":[100],"can":[101],"be":[102],"covered,":[103],"leading":[104],"improved":[106],"performance":[107],"clustering.":[111],"Experimental":[112],"results":[113],"multilingual":[116],"database":[118],"confirm":[119],"effectiveness":[121],"proposed":[124],"method.":[125]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}