{"id":"https://openalex.org/W2145795534","doi":"https://doi.org/10.1109/icassp.2009.4960624","title":"PHMM based asynchronous acoustic model for Chinese large vocabulary continuous speech recognition","display_name":"PHMM based asynchronous acoustic model for Chinese large vocabulary continuous speech recognition","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2145795534","doi":"https://doi.org/10.1109/icassp.2009.4960624","mag":"2145795534"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960624","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5114246634","display_name":"Hao Wu","orcid":"https://orcid.org/0000-0003-0518-9511"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Wu","raw_affiliation_strings":["Hearing Research Center, Key Laboratory of Machine Perception ( Ministry of Education ), Peking University, Beijing, China","Hearing Research Center, Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, 100871, China"],"affiliations":[{"raw_affiliation_string":"Hearing Research Center, Key Laboratory of Machine Perception ( Ministry of Education ), Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Hearing Research Center, Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, 100871, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084685506","display_name":"Xihong Wu","orcid":"https://orcid.org/0009-0004-5236-7469"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihong Wu","raw_affiliation_strings":["Hearing Research Center, Key Laboratory of Machine Perception ( Ministry of Education ), Peking University, Beijing, China","Hearing Research Center, Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, 100871, China"],"affiliations":[{"raw_affiliation_string":"Hearing Research Center, Key Laboratory of Machine Perception ( Ministry of Education ), Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Hearing Research Center, Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, 100871, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038249650","display_name":"Huisheng Chi","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huisheng Chi","raw_affiliation_strings":["Hearing Research Center, Key Laboratory of Machine Perception ( Ministry of Education ), Peking University, Beijing, China","Hearing Research Center, Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, 100871, China"],"affiliations":[{"raw_affiliation_string":"Hearing Research Center, Key Laboratory of Machine Perception ( Ministry of Education ), Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Hearing Research Center, Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, 100871, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5114246634"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14117131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":null,"first_page":"4477","last_page":"4480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9919000267982483,"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":0.9868999719619751,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8625496625900269},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8018853664398193},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7407463788986206},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6648886203765869},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6121828556060791},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5502772331237793},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5391120910644531},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5052950978279114},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.504607081413269},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.48954448103904724},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47695815563201904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4632076025009155},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3760581612586975},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3618980050086975},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07417955994606018},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06878030300140381}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8625496625900269},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8018853664398193},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7407463788986206},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6648886203765869},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6121828556060791},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5502772331237793},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5391120910644531},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5052950978279114},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.504607081413269},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.48954448103904724},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47695815563201904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4632076025009155},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3760581612586975},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3618980050086975},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07417955994606018},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06878030300140381},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2009.4960624","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1028.203","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1028.203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mirlab.org/conference_papers/International_Conference/ICASSP%202009/pdfs/0004477.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W326551381","https://openalex.org/W1978380426","https://openalex.org/W2124174353","https://openalex.org/W2170960573","https://openalex.org/W2476254132","https://openalex.org/W6644697353","https://openalex.org/W6685100782"],"related_works":["https://openalex.org/W2121652828","https://openalex.org/W3033124456","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W2122233706","https://openalex.org/W642007152","https://openalex.org/W2105439218","https://openalex.org/W1992225910","https://openalex.org/W3143423642","https://openalex.org/W2131711534"],"abstract_inverted_index":{"In":[0,15],"this":[1,16],"paper,":[2],"we":[3],"presented":[4],"an":[5],"asynchronous":[6],"multiple":[7],"stream":[8],"based":[9],"Chinese":[10],"tonal":[11,53,62],"acoustic":[12,28],"modeling":[13],"framework.":[14],"framework,":[17],"toneless":[18],"phonetic":[19,54],"units":[20],"and":[21,33,81,85],"tones":[22],"are":[23,40],"modeled":[24],"separately":[25],"with":[26,43],"different":[27],"features.":[29],"During":[30],"the":[31,89],"training":[32],"decoding":[34],"process,":[35],"a":[36,44,58,68],"set":[37],"of":[38],"models":[39,48],"coupled":[41],"together":[42],"product":[45],"hidden":[46],"Markov":[47],"(PHMM)":[49],"to":[50],"represent":[51],"whole":[52],"units.":[55],"Through":[56],"this,":[57],"compound":[59],"context":[60],"dependent":[61],"model":[63,76,83],"can":[64],"be":[65],"generated":[66],"from":[67],"few":[69],"simple":[70],"models.":[71],"Experiments":[72],"show":[73],"that":[74],"such":[75],"scheme":[77],"generates":[78],"more":[79],"compact":[80],"accurate":[82],"presentation":[84],"brings":[86],"improvement":[87],"on":[88],"performance":[90],"for":[91],"large":[92],"vocabulary":[93],"speech":[94],"recognition":[95],"tasks.":[96]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}