{"id":"https://openalex.org/W1245895196","doi":"https://doi.org/10.21437/interspeech.2012-402","title":"A simple and efficient method to align very long speech signals to acoustically imperfect transcriptions","display_name":"A simple and efficient method to align very long speech signals to acoustically imperfect transcriptions","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W1245895196","doi":"https://doi.org/10.21437/interspeech.2012-402","mag":"1245895196"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-402","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","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/A5067184681","display_name":"Germ\u00e1n Bordel","orcid":"https://orcid.org/0000-0003-1758-0964"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Germ\u00e1n Bordel","raw_affiliation_strings":["University of The Basque Country"],"affiliations":[{"raw_affiliation_string":"University of The Basque Country","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031896364","display_name":"Mikel Pe\u00f1agarikano","orcid":"https://orcid.org/0000-0001-6848-349X"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Mikel Penagarikano","raw_affiliation_strings":["University of the Basque Country, Leioa, Spain"],"affiliations":[{"raw_affiliation_string":"University of the Basque Country, Leioa, Spain","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084820966","display_name":"Luis Javier Rodr\u00edguez-Fuentes","orcid":"https://orcid.org/0000-0001-9313-2667"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Luis Javier Rodriguez-Fuentes","raw_affiliation_strings":["University of the Basque Country, Leioa, Spain"],"affiliations":[{"raw_affiliation_string":"University of the Basque Country, Leioa, Spain","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057476491","display_name":"Amparo Varona","orcid":"https://orcid.org/0000-0003-0255-8991"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Amparo Varona","raw_affiliation_strings":["University of the Basque Country, Leioa, Spain"],"affiliations":[{"raw_affiliation_string":"University of the Basque Country, Leioa, Spain","institution_ids":["https://openalex.org/I169108374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5067184681"],"corresponding_institution_ids":["https://openalex.org/I169108374"],"apc_list":null,"apc_paid":null,"fwci":5.5703,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.9555977,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1840","last_page":"1843"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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":0.8915709257125854},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.6997992396354675},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6296861171722412},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.6180652379989624},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5466315746307373},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5390704274177551},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48456230759620667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3960994482040405},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13203224539756775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8915709257125854},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6997992396354675},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6296861171722412},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.6180652379989624},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5466315746307373},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5390704274177551},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48456230759620667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3960994482040405},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13203224539756775},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2012-402","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W10731371","https://openalex.org/W85707815","https://openalex.org/W123891035","https://openalex.org/W2004555600","https://openalex.org/W2015412875","https://openalex.org/W2074231493","https://openalex.org/W2105961775","https://openalex.org/W2165654401","https://openalex.org/W2552637878","https://openalex.org/W2619993508","https://openalex.org/W3127686677"],"related_works":["https://openalex.org/W2374250903","https://openalex.org/W1585007175","https://openalex.org/W1546413948","https://openalex.org/W2263832889","https://openalex.org/W2243884323","https://openalex.org/W42072456","https://openalex.org/W2382521049","https://openalex.org/W4243095785","https://openalex.org/W2144385241","https://openalex.org/W4387894447"],"abstract_inverted_index":{"In":[0,106],"the":[1,7,12,41,54,66,83,91,97,111,126,132,161],"framework":[2],"of":[3,14,21,65,68],"a":[4,47,73,119,135,149,182],"contract":[5],"with":[6,31,196],"Basque":[8],"Parliament":[9],"for":[10,56,96],"subtitling":[11],"videos":[13],"bilingual":[15],"plenary":[16],"sessions,":[17],"which":[18,61],"basically":[19],"consisted":[20],"aligning":[22],"very":[23,48],"long":[24],"(around":[25],"3":[26],"hours":[27],"long)":[28],"audio":[29],"tracks":[30],"syntactically":[32],"correct":[33],"but":[34],"acoustically":[35],"inaccurate":[36],"text":[37],"transcriptions":[38],"(since":[39],"all":[40],"disfluencies,":[42],"mistakes,":[43],"etc.":[44],"were":[45],"edited),":[46],"simple":[49,101],"and":[50,90,115,154,173],"efficient":[51],"procedure":[52],"(avoiding":[53],"need":[55],"language":[57],"nor":[58],"lexical":[59],"models,":[60],"was":[62,70,93,103],"key":[63],"because":[64],"mix":[67],"languages)":[69],"developed":[71],"as":[72],"first":[74],"approach,":[75],"before":[76],"trying":[77],"more":[78,171],"complex":[79],"schemes":[80],"found":[81],"in":[82,113,168,187],"literature.":[84],"Since":[85],"it":[86,117],"worked":[87],"pretty":[88],"well":[89],"output":[92],"quite":[94],"satisfactory":[95],"intended":[98],"application,":[99],"that":[100,140],"approach":[102,112,142,191],"finally":[104],"chosen.":[105],"this":[107],"paper,":[108],"we":[109],"describe":[110],"detail":[114],"apply":[116],"to":[118,125,130,134,163],"widely":[120],"known":[121],"annotated":[122],"dataset":[123],"(specifically,":[124],"1997":[127],"Hub4":[128],"task),":[129],"allow":[131],"comparison":[133],"reference":[136],"approach.":[137],"Results":[138],"demonstrate":[139],"our":[141,190],"provides":[143],"only":[144],"slightly":[145],"worse":[146],"segmentations":[147],"at":[148,178],"much":[150,156],"lower":[151],"computational":[152],"cost":[153],"requiring":[155],"fewer":[157],"resources.":[158],"Moreover,":[159],"if":[160],"resource":[162],"be":[164,193],"segmented":[165],"includes":[166],"speech":[167,183],"two":[169],"or":[170],"languages":[172],"speakers":[174],"conmute":[175],"between":[176],"them":[177],"any":[179],"time,":[180],"applying":[181],"recognizer":[184],"becomes":[185],"unfeasible":[186],"practice,":[188],"whereas":[189],"can":[192],"still":[194],"applied":[195],"no":[197],"additional":[198],"cost.":[199]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}