{"id":"https://openalex.org/W4224935349","doi":"https://doi.org/10.1109/icassp43922.2022.9747085","title":"Neufa: Neural Network Based End-to-End Forced Alignment with Bidirectional Attention Mechanism","display_name":"Neufa: Neural Network Based End-to-End Forced Alignment with Bidirectional Attention Mechanism","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224935349","doi":"https://doi.org/10.1109/icassp43922.2022.9747085"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747085","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5047338075","display_name":"Jingbei Li","orcid":"https://orcid.org/0000-0002-6284-5979"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingbei Li","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100940419","display_name":"Yi Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Meng","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","The Chinese University of Hong Kong, China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,China","The Chinese University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018710096","display_name":"Qiao Tian","orcid":"https://orcid.org/0000-0001-8177-7724"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao Tian","raw_affiliation_strings":["ByteDance,Shanghai,China","ByteDance, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"ByteDance,Shanghai,China","institution_ids":[]},{"raw_affiliation_string":"ByteDance, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339104","display_name":"Yuping Wang","orcid":"https://orcid.org/0000-0001-6868-0004"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuping Wang","raw_affiliation_strings":["ByteDance,Shanghai,China","ByteDance, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"ByteDance,Shanghai,China","institution_ids":[]},{"raw_affiliation_string":"ByteDance, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103854502","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0001-8269-3354"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["ByteDance,Shanghai,China","ByteDance, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"ByteDance,Shanghai,China","institution_ids":[]},{"raw_affiliation_string":"ByteDance, Shanghai, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5047338075"],"corresponding_institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.9832,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.88275826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8007","last_page":"8011"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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/T12031","display_name":"Speech and dialogue systems","score":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8359693288803101},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7768617272377014},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7475882172584534},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6206822395324707},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5934717059135437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5856286883354187},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.5158674120903015},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4835629165172577},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44283628463745117},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33271893858909607}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8359693288803101},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7768617272377014},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7475882172584534},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6206822395324707},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5934717059135437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5856286883354187},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.5158674120903015},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4835629165172577},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44283628463745117},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33271893858909607},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747085","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/16","score":0.6499999761581421,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W121610373","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1556470778","https://openalex.org/W1963727751","https://openalex.org/W2059661787","https://openalex.org/W2063912635","https://openalex.org/W2076596602","https://openalex.org/W2105594594","https://openalex.org/W2133564696","https://openalex.org/W2145410271","https://openalex.org/W2191779130","https://openalex.org/W2327501763","https://openalex.org/W2747874407","https://openalex.org/W2946200149","https://openalex.org/W2963609956","https://openalex.org/W2964199361","https://openalex.org/W2964243274","https://openalex.org/W3034794073","https://openalex.org/W4295312788","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6633249632","https://openalex.org/W6679434410","https://openalex.org/W6739901393","https://openalex.org/W6746700228","https://openalex.org/W6763832098","https://openalex.org/W6766978945","https://openalex.org/W6776390925"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W2053269318","https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W4253235840","https://openalex.org/W3151937861"],"abstract_inverted_index":{"Although":[0],"deep":[1],"learning":[2,70,102,114,149],"and":[3,10,19,43,53,69,74,106,137,143,178],"end-to-end":[4,82],"models":[5,27],"have":[6],"been":[7],"widely":[8],"used":[9],"shown":[11],"their":[12],"superiority":[13],"in":[14,63,72,87,109,123,146],"automatic":[15],"speech":[16],"recognition":[17],"(ASR)":[18],"text-to-speech":[20],"(TTS)":[21],"synthesis,":[22],"state-of-the-art":[23,190],"forced":[24,83],"alignment":[25,101,116],"(FA)":[26],"are":[28,130],"still":[29],"based":[30,81,192],"on":[31,165],"hidden":[32],"Markov":[33],"model":[34],"(HMM).":[35],"HMM":[36,191],"has":[37],"limited":[38],"view":[39],"of":[40,60,103,156],"contextual":[41,67],"information":[42,68,117],"is":[44],"developed":[45],"with":[46,160,189],"long":[47,65],"pipelines,":[48],"leading":[49],"to":[50,172,182],"error":[51,163],"accumulation":[52],"unsatisfactory":[54],"performance.":[55],"Inspired":[56],"by":[57,113,139],"the":[58,100,124,133,140,154],"capability":[59],"attention":[61,92,121,127,135],"mechanism":[62,93],"capturing":[64],"term":[66],"alignments":[71],"ASR":[73,105],"TTS,":[75],"we":[76],"propose":[77],"a":[78,89,110,119,147],"neural":[79],"network":[80],"aligner":[84],"called":[85],"NeuFA,":[86],"which":[88],"novel":[90],"bidirectional":[91,115,126],"plays":[94],"an":[95],"essential":[96],"role.":[97],"NeuFA":[98],"integrates":[99],"both":[104],"TTS":[107,142],"tasks":[108,145],"unified":[111],"framework":[112],"from":[118,132,169,179],"shared":[120],"matrix":[122],"proposed":[125,158],"mechanism.":[128],"Alignments":[129],"extracted":[131],"learnt":[134],"weights":[136],"optimized":[138],"ASR,":[141],"FA":[144],"multi-task":[148],"manner.":[150],"Experimental":[151],"results":[152],"demonstrate":[153],"effectiveness":[155],"our":[157],"model,":[159],"mean":[161],"absolute":[162],"(MAE)":[164],"test":[166],"set":[167],"drops":[168],"25.8":[170],"ms":[171,174,181,184],"23.7":[173],"at":[175,185],"word":[176],"level,":[177],"18.0":[180],"15.7":[183],"phoneme":[186],"level":[187],"compared":[188],"model.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}