{"id":"https://openalex.org/W4300881239","doi":"https://doi.org/10.21437/icslp.1996-150","title":"Automatic transcription of general audio data: preliminary analyses","display_name":"Automatic transcription of general audio data: preliminary analyses","publication_year":1996,"publication_date":"1996-10-03","ids":{"openalex":"https://openalex.org/W4300881239","doi":"https://doi.org/10.21437/icslp.1996-150"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.1996-150","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1996-150","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":"conference-paper","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":false,"raw_author_name":"Michelle S. Spina","raw_affiliation_strings":["Spoken Language Systems Group Laboratory for Computer Science Massachusetts Institute of Technology Cambridge, Massachusetts 02139 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spoken Language Systems Group Laboratory for Computer Science Massachusetts Institute of Technology Cambridge, Massachusetts 02139 USA","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 Zue","raw_affiliation_strings":["Spoken Language Systems Group Laboratory for Computer Science Massachusetts Institute of Technology Cambridge, Massachusetts 02139 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spoken Language Systems Group Laboratory for Computer Science Massachusetts Institute of Technology Cambridge, Massachusetts 02139 USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.37973658,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"594","last_page":"597"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9902999997138977,"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":0.9902999997138977,"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":0.9805999994277954,"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/T10860","display_name":"Speech and Audio Processing","score":0.9088000059127808,"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/computer-science","display_name":"Computer science","score":0.735394299030304},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.614159882068634},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4186818301677704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.735394299030304},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.614159882068634},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4186818301677704},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/icslp.1996-150","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1996-150","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":3,"referenced_works":["https://openalex.org/W47510410","https://openalex.org/W2558547107","https://openalex.org/W4302805652"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"The":[0],"task":[1,14],"of":[2,17,25,43,124],"automatically":[3],"transcribing":[4],"general":[5,23],"audio":[6],"data":[7,70],"is":[8,28,128],"very":[9],"different":[10],"from":[11,72],"the":[12,31,56,104,121],"transcription":[13],"typically":[15],"required":[16],"current":[18],"automatic":[19],"speech":[20,46],"recognition":[21,47],"systems.The":[22],"goal":[24],"this":[26],"work":[27],"to":[29,40,51,54,90],"quantify":[30],"difficult":[32],"issues":[33],"posed":[34],"by":[35],"such":[36],"data,":[37,105],"thus":[38],"leading":[39],"an":[41],"understanding":[42],"how":[44],"a":[45,73,112,125],"system":[48],"may":[49],"have":[50,67],"be":[52],"altered":[53],"accommodate":[55],"added":[57],"complexities.Specifically,":[58],"we":[59,66,87],"describe":[60],"some":[61],"preliminary":[62],"analyses":[63],"and":[64,84,106],"experiments":[65],"conducted":[68],"on":[69],"collected":[71],"radio":[74],"news":[75],"program.We":[76],"found":[77],"that":[78,119],"using":[79],"relatively":[80],"straightforward":[81],"acoustic":[82],"measurements":[83],"classification":[85,95,109],"techniques,":[86],"were":[88],"able":[89],"achieve":[91],"better":[92],"than":[93],"80%":[94],"accuracy":[96,110],"for":[97,111],"seven":[98],"salient":[99],"sound":[100],"classes":[101],"present":[102],"in":[103],"nearly":[107],"94%":[108],"speech/non-speech":[113],"decision.In":[114],"addition,":[115],"lexical":[116],"analysis":[117],"revealed":[118],"while":[120],"vocabulary":[122],"size":[123],"single":[126],"broadcast":[127],"moderate,":[129],"it":[130],"grows":[131],"exponentially":[132],"as":[133],"more":[134],"shows":[135],"are":[136],"added.":[137]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}