{"id":"https://openalex.org/W30604074","doi":"https://doi.org/10.21437/eurospeech.1999-285x","title":"A new hybrid structure of speech recognizer based on HMM and neural network","display_name":"A new hybrid structure of speech recognizer based on HMM and neural network","publication_year":1999,"publication_date":"1999-09-05","ids":{"openalex":"https://openalex.org/W30604074","doi":"https://doi.org/10.21437/eurospeech.1999-285x","mag":"30604074"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1999-285x","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/eurospeech.1999-285x","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th European Conference on Speech Communication and Technology","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/A5081259452","display_name":"Jian-Lai Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jianlai Zhou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727205","display_name":"Xiaodong He","orcid":"https://orcid.org/0000-0002-9463-9168"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaodong He","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100507295","display_name":"Tiecheng Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tiecheng Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5070168391","display_name":"Fuyuan Mo","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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuyuan Mo","raw_affiliation_strings":["Institute of Acoustics,Chinese Academy of Sciences)"],"affiliations":[{"raw_affiliation_string":"Institute of Acoustics,Chinese Academy of Sciences)","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081259452"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00469385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1131","last_page":"1134"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9973000288009644,"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/T10320","display_name":"Neural Networks and Applications","score":0.995199978351593,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.817908763885498},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8061519861221313},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.7322973012924194},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7162216901779175},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5405352115631104},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.5153086185455322},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5142247676849365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5115891098976135},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.4914959669113159},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4884163737297058},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4500362277030945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.817908763885498},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8061519861221313},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7322973012924194},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7162216901779175},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5405352115631104},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.5153086185455322},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5142247676849365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5115891098976135},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.4914959669113159},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4884163737297058},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4500362277030945},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.1999-285x","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/eurospeech.1999-285x","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th European Conference on Speech Communication and Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W248072654","https://openalex.org/W1553004968","https://openalex.org/W2054584253","https://openalex.org/W2121551440","https://openalex.org/W3108739439"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W3145575561","https://openalex.org/W2001275470","https://openalex.org/W2073996508","https://openalex.org/W1591475660","https://openalex.org/W1974738623"],"abstract_inverted_index":{"In":[0,105],"this":[1,43,123],"paper,":[2],"we":[3,108],"introduced":[4],"a":[5,28,101,125],"new":[6],"framework":[7],"of":[8,42,51,70,77,83,94,103],"speech":[9,34,54],"recognizer":[10],"based":[11,53],"on":[12],"HMM":[13,38,52,71],"and":[14,91,144],"neural":[15,23,73,79,89],"net.":[16],"Unlike":[17],"the":[18,22,33,48,67,75,78,81,84,92,95,135],"traditional":[19],"hybrid":[20],"system,":[21],"net":[24],"was":[25],"used":[26],"as":[27,63],"post":[29],"processor,":[30],"which":[31],"classify":[32],"data":[35],"segmented":[36],"by":[37],"recognizer.":[39],"The":[40],"purpose":[41],"method":[44],"is":[45,124],"to":[46,65,110,133],"improve":[47,134],"top-choice":[49],"accuracy":[50,137],"recognition":[55,136],"system":[56,140],"in":[57,72,116,141],"our":[58],"lab.":[59],"Major":[60],"issues":[61],"such":[62],"how":[64],"use":[66],"segmentation":[68],"information":[69],"net,":[74,80,90],"structure":[76],"choice":[82],"error":[85],"metric":[86],"for":[87,138,146],"training":[88,96],"determination":[93],"procedure":[97],"are":[98],"investigated":[99],"within":[100],"set":[102],"experiments.":[104],"these":[106],"experiments,":[107],"attempt":[109],"recognize":[111],"68":[112],"phoneme":[113],"like":[114],"units":[115],"continuous":[117],"speech.":[118],"Our":[119],"results":[120],"indicate":[121],"that":[122],"potential":[126],"method.":[127],"About":[128],"20%":[129],"can":[130],"be":[131],"obtained":[132],"multi-speaker":[139],"syllable":[142],"level,":[143],"10%":[145],"speaker":[147],"independent":[148],"system.":[149]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}