{"id":"https://openalex.org/W142477701","doi":"https://doi.org/10.21437/eurospeech.2001-655","title":"Speech lab in a box: a Mandarin speech toolbox to jumpstart speech related research","display_name":"Speech lab in a box: a Mandarin speech toolbox to jumpstart speech related research","publication_year":2001,"publication_date":"2001-09-03","ids":{"openalex":"https://openalex.org/W142477701","doi":"https://doi.org/10.21437/eurospeech.2001-655","mag":"142477701"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2001-655","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","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/A5087298985","display_name":"Eric Chang","orcid":"https://orcid.org/0000-0002-9678-5994"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eric Chang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101597408","display_name":"Yu Shi","orcid":"https://orcid.org/0000-0003-1872-3429"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081259452","display_name":"Jian-Lai Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianlai Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5009913582","display_name":"Chao Huang","orcid":"https://orcid.org/0000-0002-9300-1787"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chao Huang","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2803,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.91934709,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2799","last_page":"2802"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9724000096321106,"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":0.9724000096321106,"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/T12031","display_name":"Speech and dialogue systems","score":0.9546999931335449,"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":0.9143000245094299,"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/toolbox","display_name":"Toolbox","score":0.8824895620346069},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8586859703063965},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8011105060577393},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.6574838757514954},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6269669532775879},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5600954294204712},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5270048975944519},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4834476411342621},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.47777020931243896},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.47133946418762207},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3829050660133362},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11740165948867798},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09545734524726868}],"concepts":[{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.8824895620346069},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8586859703063965},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8011105060577393},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6574838757514954},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6269669532775879},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5600954294204712},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5270048975944519},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4834476411342621},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.47777020931243896},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.47133946418762207},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3829050660133362},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11740165948867798},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09545734524726868},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.2001-655","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W108550785","https://openalex.org/W2075236132","https://openalex.org/W2121715942","https://openalex.org/W2161964681","https://openalex.org/W3022446722"],"related_works":["https://openalex.org/W3084276481","https://openalex.org/W4397292310","https://openalex.org/W2500421879","https://openalex.org/W2184371793","https://openalex.org/W2186688931","https://openalex.org/W4205598694","https://openalex.org/W2537969829","https://openalex.org/W2389032213","https://openalex.org/W2356192947","https://openalex.org/W4391272374"],"abstract_inverted_index":{"The":[0],"necessity":[1],"of":[2,32,47,80,86,122,128,152,166],"gathering":[3],"data":[4,34,106,115],"has":[5],"been":[6],"an":[7],"impediment":[8],"for":[9,118],"researchers":[10,41,60],"and":[11,42,114,125,137],"students":[12,43,138],"who":[13,139],"are":[14,27,69],"interested":[15],"in":[16,19,71,83,95,145,163],"getting":[17],"started":[18],"the":[20,84,96,150,155,164],"fields":[21],"related":[22],"to":[23,38,50,64,77,141,154,159],"speech":[24,88,105,146,168],"recognition.":[25,169],"We":[26,74,98],"proposing":[28],"a":[29,45,92,100,120,126],"new":[30],"approach":[31],"distributing":[33],"that":[35,68,102,133],"is":[36],"designed":[37],"quickly":[39],"help":[40,135],"achieve":[44],"set":[46,94,121],"baseline":[48,123],"results":[49,67,82],"build":[51],"upon.":[52],"Furthermore,":[53],"by":[54,90],"leveraging":[55],"publicly":[56],"available":[57],"programs,":[58],"all":[59],"will":[61],"be":[62],"able":[63],"exactly":[65],"reproduce":[66],"described":[70],"this":[72],"paper.":[73],"also":[75],"aim":[76],"facilitate":[78],"comparison":[79],"recognition":[81,89],"field":[85],"Mandarin":[87,104,167],"including":[91],"testing":[93],"toolbox.":[97],"describe":[99],"toolbox":[101],"includes":[103],"from":[107],"125":[108],"speakers,":[109],"suitable":[110],"language":[111],"model,":[112],"scripts":[113],"files":[116],"required":[117],"recreating":[119],"experiments,":[124],"copy":[127],"Microsoft":[129],"SAPI":[130],"5.0":[131],"SDK":[132],"can":[134],"professors":[136],"wish":[140],"jumpstart":[142],"research":[143],"programs":[144],"technologies.":[147],"By":[148],"lowering":[149],"barrier":[151],"entry":[153],"field,":[156],"we":[157],"hope":[158],"encourage":[160],"more":[161],"participation":[162],"study":[165]},"counts_by_year":[{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
