{"id":"https://openalex.org/W2203545501","doi":"https://doi.org/10.1109/lsp.2015.2505140","title":"Probabilistic Kernels for Improved Text-to-Speech Alignment in Long Audio Tracks","display_name":"Probabilistic Kernels for Improved Text-to-Speech Alignment in Long Audio Tracks","publication_year":2015,"publication_date":"2015-12-03","ids":{"openalex":"https://openalex.org/W2203545501","doi":"https://doi.org/10.1109/lsp.2015.2505140","mag":"2203545501"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2015.2505140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2015.2505140","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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":false,"raw_author_name":"German Bordel","raw_affiliation_strings":["Department of Electricity and Electronics, University of the Basque Country, UPV/EHU, Leioa, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electricity and Electronics, University of the Basque Country, UPV/EHU, Leioa, Spain","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":["Department of Electricity and Electronics, University of the Basque Country, UPV/EHU, Leioa, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electricity and Electronics, University of the Basque Country, UPV/EHU, 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":["Department of Electricity and Electronics, University of the Basque Country, UPV/EHU, Leioa, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electricity and Electronics, University of the Basque Country, UPV/EHU, Leioa, Spain","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"middle","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":false,"raw_author_name":"Aitor Alvarez","raw_affiliation_strings":["Human Speech and Language Technologies, Vicomtech-IK4, San Sebasti\u00e1n, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Speech and Language Technologies, Vicomtech-IK4, San Sebasti\u00e1n, Spain","institution_ids":["https://openalex.org/I4210092551"]}]},{"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":["Department of Electricity and Electronics, University of the Basque Country, UPV/EHU, Leioa, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electricity and Electronics, University of the Basque Country, UPV/EHU, Leioa, Spain","institution_ids":["https://openalex.org/I169108374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8527,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.74671053,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"23","issue":"1","first_page":"126","last_page":"129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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":0.9994000196456909,"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":0.8350797891616821},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7572821378707886},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.62259441614151},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5581144094467163},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.491879940032959},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46004346013069153},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4495207667350769},{"id":"https://openalex.org/keywords/timestamp","display_name":"Timestamp","score":0.43510133028030396},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3449791967868805},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11122429370880127},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.10579937696456909}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8350797891616821},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7572821378707886},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.62259441614151},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5581144094467163},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.491879940032959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46004346013069153},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4495207667350769},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.43510133028030396},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3449791967868805},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11122429370880127},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.10579937696456909},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2015.2505140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2015.2505140","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.800000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W10731371","https://openalex.org/W85707815","https://openalex.org/W123891035","https://openalex.org/W203760253","https://openalex.org/W1245895196","https://openalex.org/W1549877291","https://openalex.org/W1647671624","https://openalex.org/W2015412875","https://openalex.org/W2105961775","https://openalex.org/W2125670750","https://openalex.org/W2128652590","https://openalex.org/W2165654401","https://openalex.org/W2293596383","https://openalex.org/W2341824394","https://openalex.org/W2397159106","https://openalex.org/W2406366062","https://openalex.org/W3127686677","https://openalex.org/W6600436803","https://openalex.org/W6603477829","https://openalex.org/W6636915900","https://openalex.org/W6704380518","https://openalex.org/W6713747270"],"related_works":["https://openalex.org/W2060561905","https://openalex.org/W1417711376","https://openalex.org/W1986883493","https://openalex.org/W2469862403","https://openalex.org/W2166378262","https://openalex.org/W2035891203","https://openalex.org/W4379524643","https://openalex.org/W2367807705","https://openalex.org/W4285233590","https://openalex.org/W2070290693"],"abstract_inverted_index":{"The":[0,169],"synchronization":[1],"of":[2,67,74,84,112,140,148,157],"text":[3,30],"transcripts":[4],"with":[5,21],"audio":[6,25],"tracks":[7,26],"is":[8,103],"typically":[9],"solved":[10],"by":[11],"forced":[12],"alignment":[13,73],"at":[14],"the":[15,68,72,75,82,87,90,99,108,113,129,146,149,154,195],"phonetic":[16,65,79,150],"level.":[17],"However,":[18],"when":[19],"dealing":[20],"either":[22],"very":[23],"long":[24],"or":[27],"acoustically":[28],"inaccurate":[29],"transcripts,":[31],"more":[32],"complex":[33],"methods":[34],"are":[35,125],"needed,":[36],"usually":[37],"based":[38,61,127],"on":[39,62,98,128,194],"heavy":[40],"and":[41,54,71,77,102,110,152,180,188],"costly":[42],"ASR":[43],"systems.":[44],"In":[45,118],"a":[46,52,63,132,137,184,189],"previous":[47],"work,":[48],"we":[49],"showed":[50],"that":[51,131,153],"simple":[53],"lightweight":[55],"method":[56,93],"could":[57],"be":[58],"effectively":[59],"applied,":[60,126],"free":[64,76],"decoding":[66],"speech":[69,141],"signal":[70],"reference":[78,185],"sequences,":[80],"allowing":[81],"transfer":[83],"timestamps":[85],"from":[86,136],"former":[88],"to":[89,106,166],"latter.":[91],"This":[92],"has":[94],"yielded":[95],"competitive":[96],"results":[97],"Hub4-97":[100,196],"dataset":[101],"currently":[104],"applied":[105],"synchronize":[107],"videos":[109],"minutes":[111],"Basque":[114],"Parliament":[115],"plenary":[116],"sessions.":[117],"this":[119,158,174],"paper,":[120],"probabilistic":[121,155,170],"kernels":[122,164,171,179],"(similarity":[123],"functions)":[124],"hypothesis":[130],"confusion":[133],"matrix":[134],"computed":[135],"large":[138],"corpus":[139],"conveys":[142],"key":[143],"information":[144,159],"about":[145],"behavior":[147],"decoder,":[151],"interpretation":[156],"may":[160],"help":[161],"design":[162],"informative":[163],"leading":[165],"improved":[167],"alignments.":[168],"proposed":[172],"in":[173,192],"work":[175],"outperform":[176],"our":[177],"baseline":[178],"other":[181],"alternatives,":[182],"including":[183],"ASR-based":[186],"approach":[187],"knowledge-based":[190],"kernel,":[191],"experiments":[193],"dataset.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
