{"id":"https://openalex.org/W2128652590","doi":"https://doi.org/10.1109/icassp.2014.6854812","title":"Long audio alignment for automatic subtitling using different phone-relatedness measures","display_name":"Long audio alignment for automatic subtitling using different phone-relatedness measures","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2128652590","doi":"https://doi.org/10.1109/icassp.2014.6854812","mag":"2128652590"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5063619413","display_name":"Aitor \u00c1lvarez","orcid":"https://orcid.org/0000-0002-7938-4486"},"institutions":[{"id":"https://openalex.org/I4210092551","display_name":"Vicomtech","ror":"https://ror.org/0023sah13","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210092551"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Aitor Alvarez","raw_affiliation_strings":["Human Speech and Language Technologies, Vicomtech-IK4, San Sebasti\u00e1n, Spain","Human Speech & Language Technol., Vicomtech-IK4, San Sebastia\u0301n, Spain"],"affiliations":[{"raw_affiliation_string":"Human Speech and Language Technologies, Vicomtech-IK4, San Sebasti\u00e1n, Spain","institution_ids":["https://openalex.org/I4210092551"]},{"raw_affiliation_string":"Human Speech & Language Technol., Vicomtech-IK4, San Sebastia\u0301n, Spain","institution_ids":["https://openalex.org/I4210092551"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000869612","display_name":"Haritz Arzelus","orcid":"https://orcid.org/0000-0002-0731-1317"},"institutions":[{"id":"https://openalex.org/I4210092551","display_name":"Vicomtech","ror":"https://ror.org/0023sah13","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210092551"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Haritz Arzelus","raw_affiliation_strings":["Human Speech and Language Technologies, Vicomtech-IK4, San Sebasti\u00e1n, Spain","Human Speech & Language Technol., Vicomtech-IK4, San Sebastia\u0301n, Spain"],"affiliations":[{"raw_affiliation_string":"Human Speech and Language Technologies, Vicomtech-IK4, San Sebasti\u00e1n, Spain","institution_ids":["https://openalex.org/I4210092551"]},{"raw_affiliation_string":"Human Speech & Language Technol., Vicomtech-IK4, San Sebastia\u0301n, Spain","institution_ids":["https://openalex.org/I4210092551"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000811543","display_name":"Pablo Ruiz Fabo","orcid":"https://orcid.org/0000-0002-4349-4835"},"institutions":[{"id":"https://openalex.org/I4210092551","display_name":"Vicomtech","ror":"https://ror.org/0023sah13","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210092551"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pablo Ruiz","raw_affiliation_strings":["Human Speech and Language Technologies, Vicomtech-IK4, San Sebasti\u00e1n, Spain","Human Speech & Language Technol., Vicomtech-IK4, San Sebastia\u0301n, Spain"],"affiliations":[{"raw_affiliation_string":"Human Speech and Language Technologies, Vicomtech-IK4, San Sebasti\u00e1n, Spain","institution_ids":["https://openalex.org/I4210092551"]},{"raw_affiliation_string":"Human Speech & Language Technol., Vicomtech-IK4, San Sebastia\u0301n, Spain","institution_ids":["https://openalex.org/I4210092551"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063619413"],"corresponding_institution_ids":["https://openalex.org/I4210092551"],"apc_list":null,"apc_paid":null,"fwci":3.2721,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.93083479,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"116","issue":null,"first_page":"6280","last_page":"6284"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9979000091552734,"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":0.9979000091552734,"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":0.994700014591217,"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":0.9944999814033508,"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":0.7928812503814697},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7830991744995117},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6737275123596191},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.533100962638855},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42015576362609863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36835557222366333},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.15941432118415833},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10096383094787598}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7928812503814697},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7830991744995117},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6737275123596191},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.533100962638855},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42015576362609863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36835557222366333},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.15941432118415833},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10096383094787598},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"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":16,"referenced_works":["https://openalex.org/W10731371","https://openalex.org/W175761898","https://openalex.org/W1245895196","https://openalex.org/W2087769310","https://openalex.org/W2105961775","https://openalex.org/W2125670750","https://openalex.org/W2165654401","https://openalex.org/W2306803708","https://openalex.org/W2341824394","https://openalex.org/W2587093408","https://openalex.org/W3127686677","https://openalex.org/W4387428949","https://openalex.org/W6600436803","https://openalex.org/W6607111733","https://openalex.org/W6628079055","https://openalex.org/W6704380518"],"related_works":["https://openalex.org/W2370205415","https://openalex.org/W4387493491","https://openalex.org/W2904225411","https://openalex.org/W4388331409","https://openalex.org/W2169921015","https://openalex.org/W2651370314","https://openalex.org/W1961128080","https://openalex.org/W2323686453","https://openalex.org/W2061937230","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"long":[3],"audio":[4],"alignment":[5,32,56],"systems":[6],"for":[7,48],"Spanish":[8],"and":[9,41,77,100],"English":[10],"are":[11,20,89,112],"presented":[12],"in":[13,44,114],"an":[14],"automatic":[15],"subtitling":[16],"scenario.":[17],"Pre-recorded":[18],"contents":[19],"automatically":[21,38],"recognized":[22],"at":[23,98],"phoneme":[24],"level":[25],"by":[26],"language-dependent":[27],"phone":[28,68,72],"decoders.":[29],"A":[30],"dynamic-programming":[31],"algorithm":[33,57],"finds":[34],"matches":[35],"between":[36],"the":[37,42,45,49,55,85,115],"decoded":[39],"phones":[40],"ones":[43],"phonetic":[46],"transcription":[47],"content's":[50],"script.":[51],"The":[52,103],"accuracy":[53],"of":[54],"is":[58],"evaluated":[59],"when":[60],"applying":[61],"three":[62,86],"non-binary":[63,104],"scoring":[64],"matrices":[65,88,105],"based":[66],"on":[67,74,78],"confusion-pairs":[69],"from":[70],"each":[71],"decoder,":[73],"phonological":[75],"similarity":[76],"human":[79],"perception":[80],"errors.":[81],"Alignment":[82],"results":[83,92],"with":[84,93],"continuous-score":[87],"compared":[90],"to":[91],"a":[94],"baseline":[95],"binary":[96],"matrix,":[97],"word":[99],"subtitle":[101],"levels.":[102],"achieved":[106],"clearly":[107],"better":[108],"results.":[109],"Matrix":[110],"samples":[111],"given":[113],"project's":[116],"website.":[117]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
