{"id":"https://openalex.org/W4392902865","doi":"https://doi.org/10.1109/icassp48485.2024.10446111","title":"Less Peaky and More Accurate CTC Forced Alignment by Label Priors","display_name":"Less Peaky and More Accurate CTC Forced Alignment by Label Priors","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902865","doi":"https://doi.org/10.1109/icassp48485.2024.10446111"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5108823342","display_name":"Ruizhe Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruizhe Huang","raw_affiliation_strings":["Johns Hopkins University,USA","Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088378499","display_name":"Xiaohui Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaohui Zhang","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031088292","display_name":"Zhaoheng Ni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaoheng Ni","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101629398","display_name":"Li Sun","orcid":"https://orcid.org/0000-0002-0393-8665"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Sun","raw_affiliation_strings":["Boston University,USA","Boston University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University,USA","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Boston University, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025983396","display_name":"Moto Hira","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moto Hira","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021004964","display_name":"Jeff Hwang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeff Hwang","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028956985","display_name":"Vimal Manohar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vimal Manohar","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028944337","display_name":"Vineel Pratap","orcid":"https://orcid.org/0000-0003-3333-910X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vineel Pratap","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014455067","display_name":"Matthew Wiesner","orcid":"https://orcid.org/0000-0001-8653-7738"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Wiesner","raw_affiliation_strings":["Johns Hopkins University,USA","Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Melon University,USA","Carnegie Melon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Melon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Melon University, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Xiaomi Corp.,Beijing,China","Xiaomi Corp., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp.,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Johns Hopkins University,USA","Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":12,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0547,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.92059413,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11831","last_page":"11835"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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":0.9973000288009644,"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":0.7613271474838257},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.5965993404388428},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5887182354927063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5116420388221741},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4970288574695587},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.4524582028388977},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.44719481468200684},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3693752884864807},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.3441293239593506}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7613271474838257},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5965993404388428},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5887182354927063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5116420388221741},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4970288574695587},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.4524582028388977},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.44719481468200684},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3693752884864807},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3441293239593506},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1548813916","https://openalex.org/W1556470778","https://openalex.org/W2127141656","https://openalex.org/W2144499799","https://openalex.org/W2145410271","https://openalex.org/W2160815625","https://openalex.org/W2404463488","https://openalex.org/W2747874407","https://openalex.org/W2748816379","https://openalex.org/W2891267443","https://openalex.org/W2892209435","https://openalex.org/W2963250244","https://openalex.org/W3004280449","https://openalex.org/W3019794902","https://openalex.org/W3036601975","https://openalex.org/W3043783436","https://openalex.org/W3097777922","https://openalex.org/W3127686677","https://openalex.org/W3167895882","https://openalex.org/W3207272747","https://openalex.org/W4224935349","https://openalex.org/W4225741214","https://openalex.org/W4243389914","https://openalex.org/W4306705025","https://openalex.org/W4311000453","https://openalex.org/W4372262245","https://openalex.org/W4378105483","https://openalex.org/W4384828046","https://openalex.org/W4385822293","https://openalex.org/W4389883851","https://openalex.org/W4391021755","https://openalex.org/W6633249632","https://openalex.org/W6754747464","https://openalex.org/W6780218876","https://openalex.org/W6796656850","https://openalex.org/W6845608264","https://openalex.org/W6847363464","https://openalex.org/W6852909395"],"related_works":["https://openalex.org/W2580650124","https://openalex.org/W4386190339","https://openalex.org/W2968424575","https://openalex.org/W2562263695","https://openalex.org/W2135187896","https://openalex.org/W2147201983","https://openalex.org/W2015518264","https://openalex.org/W2795035211","https://openalex.org/W2160108762","https://openalex.org/W2017034551"],"abstract_inverted_index":{"Connectionist":[0],"temporal":[1],"classification":[2],"(CTC)":[3],"models":[4],"are":[5,70,182],"known":[6],"to":[7,89],"have":[8],"peaky":[9,44,84],"output":[10],"distributions.":[11],"Such":[12],"behavior":[13,45],"is":[14,87],"not":[15],"a":[16,77,108,167],"problem":[17],"for":[18,46,52,111],"automatic":[19],"speech":[20],"recognition":[21],"(ASR),":[22],"but":[23],"it":[24],"can":[25],"cause":[26],"inaccurate":[27],"forced":[28,53],"alignments":[29],"(FA),":[30],"especially":[31],"at":[32,41],"finer":[33],"granularity,":[34],"e.g.,":[35],"phoneme":[36,122],"level.":[37],"This":[38],"paper":[39],"aims":[40],"alleviating":[42],"the":[43,62,93,96,103,132,139],"CTC":[47,80,105],"and":[48,72,86,107,123,128,134,172,179],"improve":[49],"its":[50],"suitability":[51],"alignment":[54,65],"generation,":[55],"by":[56,117],"leveraging":[57],"label":[58],"priors,":[59],"so":[60],"that":[61],"scores":[63],"of":[64,95],"paths":[66],"containing":[67],"fewer":[68],"blanks":[69],"boosted":[71],"maximized":[73],"during":[74],"training.":[75],"As":[76],"result,":[78],"our":[79,149,164],"model":[81,106,181],"produces":[82],"less":[83],"posteriors":[85],"able":[88],"more":[90],"accurately":[91],"predict":[92],"offset":[94,115],"tokens":[97],"besides":[98],"their":[99],"onset.":[100],"It":[101],"outperforms":[102],"standard":[104],"heuristics-based":[109],"approach":[110],"obtaining":[112],"CTC\u2019s":[113],"token":[114],"timestamps":[116],"12":[118],"\u2212":[119],"40%":[120],"in":[121,184],"word":[124],"boundary":[125],"errors":[126],"(PBE":[127],"WBE)":[129],"measured":[130],"on":[131,153,155,161],"Buckeye":[133],"TIMIT":[135],"data.":[136],"Compared":[137],"with":[138],"most":[140],"widely":[141],"used":[142],"FA":[143],"toolkit":[144],"Montreal":[145],"Forced":[146],"Aligner":[147],"(MFA),":[148],"method":[150,165],"performs":[151],"similarly":[152],"PBE/WBE":[154],"Buckeye,":[156],"yet":[157],"falls":[158],"behind":[159],"MFA":[160],"TIMIT.":[162],"Nevertheless,":[163],"has":[166],"much":[168],"simpler":[169],"training":[170,177],"pipeline":[171],"better":[173],"runtime":[174],"efficiency.":[175],"Our":[176],"recipe":[178],"pretrained":[180],"released":[183],"TorchAudio.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}