{"id":"https://openalex.org/W2962768833","doi":"https://doi.org/10.1109/icassp.2019.8683607","title":"When CTC Training Meets Acoustic Landmarks","display_name":"When CTC Training Meets Acoustic Landmarks","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2962768833","doi":"https://doi.org/10.1109/icassp.2019.8683607","mag":"2962768833"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5102958744","display_name":"Di He","orcid":"https://orcid.org/0000-0001-5185-7408"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Di He","raw_affiliation_strings":["ECE, Coordinated Science Lab, and Beckman Institute, University of Illinois, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"ECE, Coordinated Science Lab, and Beckman Institute, University of Illinois, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059726557","display_name":"Xuesong Yang","orcid":"https://orcid.org/0000-0001-8625-5044"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuesong Yang","raw_affiliation_strings":["ECE, Coordinated Science Lab, and Beckman Institute, University of Illinois, Urbana, IL, USA","Amazon Alexa Speech, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"ECE, Coordinated Science Lab, and Beckman Institute, University of Illinois, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Amazon Alexa Speech, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026225097","display_name":"Boon Pang Lim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boon Pang Lim","raw_affiliation_strings":["Novumind Inc, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Novumind Inc, Santa Clara, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101451337","display_name":"Yi Liang","orcid":"https://orcid.org/0000-0002-6622-8919"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Liang","raw_affiliation_strings":["ECE, Coordinated Science Lab, and Beckman Institute, University of Illinois, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"ECE, Coordinated Science Lab, and Beckman Institute, University of Illinois, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["ECE, Coordinated Science Lab, and Beckman Institute, University of Illinois, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"ECE, Coordinated Science Lab, and Beckman Institute, University of Illinois, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056321228","display_name":"Deming Chen","orcid":"https://orcid.org/0000-0002-3016-0270"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deming Chen","raw_affiliation_strings":["ECE, Coordinated Science Lab, and Beckman Institute, University of Illinois, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"ECE, Coordinated Science Lab, and Beckman Institute, University of Illinois, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102958744"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.8401,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.80148542,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5996","last_page":"6000"},"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":0.9998999834060669,"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":0.9998000264167786,"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/timit","display_name":"TIMIT","score":0.9129341840744019},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8279701471328735},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6942480206489563},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5524413585662842},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5420819520950317},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.4431374669075012},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4312000870704651},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.41624945402145386}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.9129341840744019},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8279701471328735},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6942480206489563},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5524413585662842},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5420819520950317},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.4431374669075012},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4312000870704651},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.41624945402145386},{"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.2019.8683607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W16621805","https://openalex.org/W72620147","https://openalex.org/W1489125746","https://openalex.org/W1533416326","https://openalex.org/W1533861849","https://openalex.org/W1553004968","https://openalex.org/W1967177300","https://openalex.org/W2024490156","https://openalex.org/W2030909238","https://openalex.org/W2032759346","https://openalex.org/W2078046486","https://openalex.org/W2102113734","https://openalex.org/W2119155265","https://openalex.org/W2127141656","https://openalex.org/W2193413348","https://openalex.org/W2395416438","https://openalex.org/W2562588230","https://openalex.org/W2622313002","https://openalex.org/W2759071281","https://openalex.org/W2787455262","https://openalex.org/W2794550958","https://openalex.org/W2803405196","https://openalex.org/W2952976827","https://openalex.org/W2963211739","https://openalex.org/W2963266252","https://openalex.org/W2963920996","https://openalex.org/W3104406212","https://openalex.org/W3104948029","https://openalex.org/W3127686677","https://openalex.org/W4242640703","https://openalex.org/W6602958598","https://openalex.org/W6629052376","https://openalex.org/W6631943919","https://openalex.org/W6675365184","https://openalex.org/W6687566353"],"related_works":["https://openalex.org/W3134920593","https://openalex.org/W2153098279","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2994894110","https://openalex.org/W4377862891","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W36113703"],"abstract_inverted_index":{"Connectionist":[0],"temporal":[1],"classification":[2],"(CTC)":[3],"provides":[4],"an":[5],"end-to-end":[6],"acoustic":[7,41,49,90,102,153],"model":[8],"(AM)":[9],"training":[10,54],"strategy.":[11],"CTC":[12,36,53,81,88],"learns":[13],"accurate":[14],"AMs":[15],"without":[16],"time-aligned":[17],"phonetic":[18],"transcription,":[19],"but":[20],"sometimes":[21],"fails":[22],"to":[23,51,79,146],"converge,":[24],"especially":[25],"in":[26,116,148],"resource-constrained":[27],"scenarios.":[28],"In":[29],"this":[30],"paper,":[31],"the":[32,144,150],"convergence":[33],"properties":[34],"of":[35,48,152],"are":[37,99,143],"improved":[38],"by":[39,101],"incorporating":[40],"landmarks.":[42,103],"We":[43,66],"tailored":[44],"a":[45,157],"new":[46,68],"set":[47],"landmarks":[50],"help":[52],"converge":[55,92],"more":[56],"rapidly":[57],"and":[58,76,95,136],"smoothly":[59],"while":[60],"also":[61,129],"reducing":[62],"recognition":[63],"error":[64,118],"rates.":[65],"leveraged":[67],"target":[69,109],"label":[70],"sequences":[71],"mixed":[72,108],"with":[73,107],"both":[74],"phone":[75,117],"manner":[77],"changes":[78],"guide":[80],"training.":[82],"Experiments":[83],"on":[84,123,131,156],"TIMIT":[85,138],"demonstrated":[86],"that":[87],"based":[89],"models":[91,105],"significantly":[93],"faster":[94],"smoother":[96],"when":[97],"they":[98],"augmented":[100],"The":[104],"pretrained":[106],"labels":[110],"can":[111],"be":[112],"further":[113],"finetuned,":[114],"resulting":[115],"rates":[119],"8.72%":[120],"below":[121],"baseline":[122],"TIMIT.":[124],"Consistent":[125],"performance":[126],"gain":[127],"is":[128],"observed":[130],"WSJ":[132],"(a":[133],"larger":[134],"corpus)":[135],"reduced":[137],"(smaller).":[139],"With":[140],"WSJ,":[141],"we":[142],"first":[145],"succeed":[147],"verifying":[149],"effectiveness":[151],"landmark":[154],"theory":[155],"mid-sized":[158],"ASR":[159],"task.":[160]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}