{"id":"https://openalex.org/W2015412875","doi":"https://doi.org/10.1109/icme.2007.4284627","title":"Alignment of Speech to Highly Imperfect Text Transcriptions","display_name":"Alignment of Speech to Highly Imperfect Text Transcriptions","publication_year":2007,"publication_date":"2007-07-01","ids":{"openalex":"https://openalex.org/W2015412875","doi":"https://doi.org/10.1109/icme.2007.4284627","mag":"2015412875"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2007.4284627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2007.4284627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia and Expo, 2007 IEEE International Conference on","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/A5040143997","display_name":"Alexander Haubold","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Haubold","raw_affiliation_strings":["Department of Computer Science, Columbia University, USA","Columbia University, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Columbia University, USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University, New York","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088235357","display_name":"John R. Kender","orcid":"https://orcid.org/0009-0009-2522-053X"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Kender","raw_affiliation_strings":["Department of Computer Science, Columbia University, USA","Columbia University, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Columbia University, USA","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University, New York","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":2.1118,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.88084703,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"224","last_page":"227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9988999962806702,"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":0.9961000084877014,"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":0.7767765522003174},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7481738924980164},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7468412518501282},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.6299867033958435},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5072564482688904},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4619244933128357},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4606729745864868},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4494733512401581},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4455118775367737},{"id":"https://openalex.org/keywords/presentation","display_name":"Presentation (obstetrics)","score":0.43845903873443604},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4106309413909912},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07463401556015015},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07239797711372375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7767765522003174},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7481738924980164},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7468412518501282},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.6299867033958435},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5072564482688904},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4619244933128357},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4606729745864868},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4494733512401581},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4455118775367737},{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.43845903873443604},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4106309413909912},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07463401556015015},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07239797711372375},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2007.4284627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2007.4284627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia and Expo, 2007 IEEE International Conference on","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W10731371","https://openalex.org/W85707815","https://openalex.org/W2137537225","https://openalex.org/W2950367758","https://openalex.org/W6600436803"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W1909292483","https://openalex.org/W1428730622","https://openalex.org/W1658560081","https://openalex.org/W2146616055","https://openalex.org/W596245619","https://openalex.org/W2254895521","https://openalex.org/W2251422729"],"abstract_inverted_index":{"We":[0,74],"introduce":[1],"a":[2,54,95],"novel":[3],"and":[4,28,62],"inexpensive":[5],"approach":[6,51],"for":[7,25,79,107],"the":[8,59,66,72,77],"temporal":[9],"alignment":[10,90],"of":[11,56,68,98,116,130],"speech":[12,19,60],"to":[13,65,86],"highly":[14,45],"imperfect":[15],"transcripts":[16],"from":[17,71,84],"automatic":[18],"recognition":[20],"(ASR).":[21],"Transcripts":[22],"are":[23],"generated":[24,124],"extended":[26],"lecture":[27],"presentation":[29],"videos,":[30],"which":[31],"in":[32,44,58],"some":[33],"cases":[34],"feature":[35],"more":[36,108,126],"than":[37,109,127],"30":[38,103],"speakers":[39],"with":[40],"different":[41],"accents,":[42],"resulting":[43],"varying":[46],"transcription":[47],"qualities.":[48],"In":[49],"our":[50],"we":[52],"detect":[53],"subset":[55],"phonemes":[57,69,99],"track,":[61],"align":[63],"them":[64],"sequence":[67],"extracted":[70],"transcript.":[73],"report":[75],"on":[76,119],"results":[78],"4":[80],"speech-transcript":[81],"sets":[82],"ranging":[83],"22":[85],"108":[87],"minutes.":[88],"The":[89],"performance":[91],"is":[92,132],"promising,":[93],"showing":[94],"correct":[96],"matching":[97],"within":[100,135],"10,":[101],"20,":[102],"second":[104],"error":[105],"margins":[106],"60":[110],"%,":[111,113],"75":[112,128],"90":[114],"%":[115,129],"text,":[117],"respectively,":[118],"average.":[120],"For":[121],"perfect":[122],"manually":[123],"transcripts,":[125],"text":[131],"correctly":[133],"aligned":[134],"5":[136],"seconds.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
