{"id":"https://openalex.org/W4300991416","doi":"https://doi.org/10.21437/icslp.1996-587","title":"Speaker-independent dictation of Chinese speech with 32k vocabulary","display_name":"Speaker-independent dictation of Chinese speech with 32k vocabulary","publication_year":1996,"publication_date":"1996-10-03","ids":{"openalex":"https://openalex.org/W4300991416","doi":"https://doi.org/10.21437/icslp.1996-587"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.1996-587","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1996-587","pdf_url":null,"source":{"id":"https://openalex.org/S4363607739","display_name":"4th International Conference on Spoken Language Processing (ICSLP 1996)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4th International Conference on Spoken Language Processing (ICSLP 1996)","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/A5100439925","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0002-1165-7302"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Speech Research Group, National Lab of Pattern Recognition Institute of Automation,Chinese Academy of Sciences Beijing 100080 , P.R"],"affiliations":[{"raw_affiliation_string":"Speech Research Group, National Lab of Pattern Recognition Institute of Automation,Chinese Academy of Sciences Beijing 100080 , P.R","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101723903","display_name":"Bing Ma","orcid":"https://orcid.org/0000-0003-1226-3281"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Ma","raw_affiliation_strings":["Speech Research Group, National Lab of Pattern Recognition Institute of Automation,Chinese Academy of Sciences Beijing 100080 , P.R"],"affiliations":[{"raw_affiliation_string":"Speech Research Group, National Lab of Pattern Recognition Institute of Automation,Chinese Academy of Sciences Beijing 100080 , P.R","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109291841","display_name":"Shuwu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuwu Zhang","raw_affiliation_strings":["Speech Research Group, National Lab of Pattern Recognition Institute of Automation,Chinese Academy of Sciences Beijing 100080 , P.R"],"affiliations":[{"raw_affiliation_string":"Speech Research Group, National Lab of Pattern Recognition Institute of Automation,Chinese Academy of Sciences Beijing 100080 , P.R","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079654088","display_name":"Fei Qu","orcid":"https://orcid.org/0000-0002-5394-9813"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Qu","raw_affiliation_strings":["Speech Research Group, National Lab of Pattern Recognition Institute of Automation,Chinese Academy of Sciences Beijing 100080 , P.R"],"affiliations":[{"raw_affiliation_string":"Speech Research Group, National Lab of Pattern Recognition Institute of Automation,Chinese Academy of Sciences Beijing 100080 , P.R","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210094879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111409314","display_name":"Taiyi Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taiyi Huang","raw_affiliation_strings":["Speech Research Group, National Lab of Pattern Recognition Institute of Automation,Chinese Academy of Sciences Beijing 100080 , P.R"],"affiliations":[{"raw_affiliation_string":"Speech Research Group, National Lab of Pattern Recognition Institute of Automation,Chinese Academy of Sciences Beijing 100080 , P.R","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210094879"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100439925"],"corresponding_institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.52692714,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2320","last_page":"2323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9850999712944031,"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":0.9850999712944031,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9739000201225281,"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/dictation","display_name":"Dictation","score":0.9638197422027588},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7294998168945312},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6772372722625732},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6272838711738586},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4159579575061798},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.27450141310691833}],"concepts":[{"id":"https://openalex.org/C2779077324","wikidata":"https://www.wikidata.org/wiki/Q1087138","display_name":"Dictation","level":2,"score":0.9638197422027588},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7294998168945312},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6772372722625732},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6272838711738586},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4159579575061798},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.27450141310691833},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/icslp.1996-587","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1996-587","pdf_url":null,"source":{"id":"https://openalex.org/S4363607739","display_name":"4th International Conference on Spoken Language Processing (ICSLP 1996)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4th International Conference on Spoken Language Processing (ICSLP 1996)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2059907907","https://openalex.org/W2077895339","https://openalex.org/W2127364766","https://openalex.org/W2147018861","https://openalex.org/W2404240577","https://openalex.org/W2405839266"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2353325398","https://openalex.org/W2558599680","https://openalex.org/W2367608902","https://openalex.org/W2359823483","https://openalex.org/W2392667367","https://openalex.org/W2381559703","https://openalex.org/W2353027778","https://openalex.org/W2381835873"],"abstract_inverted_index":{"While":[0],"early":[1],"machines":[2],"adopted":[3],"isolated":[4],"syllable":[5],"as":[6,67],"input":[7],"units":[8],"and":[9,33,64],"needed":[10],"boring":[11],"enrollment,":[12],"our":[13],"research":[14],"focus":[15],"on":[16,83],"the":[17,48,54,73],"speaker-independent,":[18],"word-based":[19],"dictation.A":[20],"deliberately":[21],"designed":[22],"120-speaker":[23],"database":[24],"was":[25],"built":[26],"for":[27],"training":[28],";":[29],"inter-syllable":[30],"context":[31],",tonal":[32],"endpoint":[34],"dependent":[35],"acoustic":[36,45],"model":[37],"are":[38],"applied":[39],"with":[40],"promising":[41],"MFCC":[42],"feature;":[43],"Two-pass":[44],"matching":[46],"accelerates":[47],"recognition":[49],"making":[50],"fully":[51],"advantage":[52],"of":[53,57],"monosyllabic":[55],"structure":[56],"Chinese":[58],"speech;":[59],"A":[60],"complete":[61],"word":[62],"bigram":[63],"trigram":[65],"serve":[66],"language":[68],"processing":[69],"module.With":[70],"all":[71],"efforts,":[72],"system":[74],"reaches":[75],"90%":[76],"character":[77],"accuracy":[78],"performing":[79],"in":[80],"almost":[81],"real-time":[82],"Pentium":[84],"PC":[85],"without":[86],"DSP":[87],"help.":[88]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
