{"id":"https://openalex.org/W2106472082","doi":"https://doi.org/10.21437/eurospeech.1997-445","title":"Automatic transcription of general audio data: effect of environment segmentation on phonetic recognition 1","display_name":"Automatic transcription of general audio data: effect of environment segmentation on phonetic recognition 1","publication_year":1997,"publication_date":"1997-09-22","ids":{"openalex":"https://openalex.org/W2106472082","doi":"https://doi.org/10.21437/eurospeech.1997-445","mag":"2106472082"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1997-445","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","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/A5113665460","display_name":"Michelle S. Spina","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michelle S. Spina","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109575396","display_name":"Victor W. Zue","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Victor W. Zue","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5113665460"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.853,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77213264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1547","last_page":"1550"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9934999942779541,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9934999942779541,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9922999739646912,"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":0.9922000169754028,"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/word-error-rate","display_name":"Word error rate","score":0.8033132553100586},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7957563400268555},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7642109394073486},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6399263739585876},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5723687410354614},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5506904125213623},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.484408438205719},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4589157998561859},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.42220938205718994},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4179896116256714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41066351532936096},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3988625407218933},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.349550724029541},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33529388904571533},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2959741950035095},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06517624855041504}],"concepts":[{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.8033132553100586},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7957563400268555},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7642109394073486},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6399263739585876},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5723687410354614},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5506904125213623},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.484408438205719},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4589157998561859},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.42220938205718994},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4179896116256714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41066351532936096},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3988625407218933},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.349550724029541},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33529388904571533},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2959741950035095},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06517624855041504},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/eurospeech.1997-445","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.35.4961","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.35.4961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sls.lcs.mit.edu/spina/euro97.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.550000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1877154798","https://openalex.org/W1957105039","https://openalex.org/W1991133427","https://openalex.org/W2136439176","https://openalex.org/W2149007717"],"related_works":["https://openalex.org/W200981350","https://openalex.org/W4386907265","https://openalex.org/W2058752985","https://openalex.org/W2293740626","https://openalex.org/W2763412546","https://openalex.org/W1499712254","https://openalex.org/W2915347927","https://openalex.org/W2157598242","https://openalex.org/W2037564206","https://openalex.org/W4385611764"],"abstract_inverted_index":{"The":[0,21],"task":[1,52],"of":[2,24,44,80,96,107,113,144],"automatically":[3],"transcribing":[4],"general":[5,22],"audio":[6],"data":[7,54,83,108],"is":[8,27,67,72],"very":[9],"different":[10,45],"from":[11,56],"those":[12],"usually":[13],"confronted":[14],"by":[15],"current":[16],"automatic":[17],"speech":[18],"recognition":[19,51,93],"systems.":[20],"goal":[23],"our":[25],"work":[26],"to":[28,68,75],"determine":[29],"the":[30,42],"optimal":[31],"training":[32],"strategy":[33],"for":[34,84],"recognizing":[35],"such":[36],"data.":[37,131],"Specifically,":[38],"we":[39,133],"have":[40],"studied":[41],"effects":[43],"speaking":[46,114,150],"environments":[47],"on":[48],"a":[49,57,65,77,89,100,111,125,139],"phonetic":[50,92],"using":[53],"collected":[55],"radio":[58],"news":[59],"program.":[60],"We":[61,116],"found":[62,117,134],"that":[63,118,135],"if":[64],"singlerecognizer":[66],"be":[69,122],"used,":[70],"it":[71],"more":[73],"effective":[74],"use":[76],"smaller":[78],"amount":[79,106],"homogeneous,":[81],"clean":[82],"training.":[85],"This":[86],"approach":[87,137],"yielded":[88,138],"decrease":[90,140],"in":[91,141],"error":[94,142,152],"rate":[95,143,153],"over":[97,99],"26%":[98],"system":[101],"trained":[102,128],"with":[103,124,129,147],"an":[104],"equivalent":[105],"which":[109],"contained":[110],"variety":[112],"environments.":[115],"additional":[119],"gains":[120],"can":[121],"made":[123],"multiple-recognizer":[126],"system,":[127],"environment-specific":[130],"Overall,":[132],"this":[136],"nearly":[145],"2%,":[146],"some":[148],"individual":[149],"environments'":[151],"decre...":[154]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}