{"id":"https://openalex.org/W3082819093","doi":"https://doi.org/10.1109/spcom50965.2020.9179519","title":"Jointly learning to align and transcribe using attention-based alignment and uncertainty-to-weigh losses","display_name":"Jointly learning to align and transcribe using attention-based alignment and uncertainty-to-weigh losses","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3082819093","doi":"https://doi.org/10.1109/spcom50965.2020.9179519","mag":"3082819093"},"language":"en","primary_location":{"id":"doi:10.1109/spcom50965.2020.9179519","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom50965.2020.9179519","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Signal Processing and Communications (SPCOM)","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/A5008362246","display_name":"Shreekantha Nadig","orcid":null},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Shreekantha Nadig","raw_affiliation_strings":["International Institute of Information Technology Bangalore (IIIT-B), Bangalore, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Bangalore (IIIT-B), Bangalore, India","institution_ids":["https://openalex.org/I181514455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006011837","display_name":"Sumit Chakraborty","orcid":"https://orcid.org/0000-0002-1387-0385"},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sumit Chakraborty","raw_affiliation_strings":["International Institute of Information Technology Bangalore (IIIT-B), Bangalore, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Bangalore (IIIT-B), Bangalore, India","institution_ids":["https://openalex.org/I181514455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113935679","display_name":"Anuj Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anuj Shah","raw_affiliation_strings":["International Institute of Information Technology Bangalore (IIIT-B), Bangalore, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Bangalore (IIIT-B), Bangalore, India","institution_ids":["https://openalex.org/I181514455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075911570","display_name":"Chaitanay Sharma","orcid":null},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chaitanay Sharma","raw_affiliation_strings":["International Institute of Information Technology Bangalore (IIIT-B), Bangalore, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Bangalore (IIIT-B), Bangalore, India","institution_ids":["https://openalex.org/I181514455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036811576","display_name":"V. Ramasubramanian","orcid":"https://orcid.org/0000-0002-0676-9174"},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"V. Ramasubramanian","raw_affiliation_strings":["International Institute of Information Technology Bangalore (IIIT-B), Bangalore, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Bangalore (IIIT-B), Bangalore, India","institution_ids":["https://openalex.org/I181514455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078955137","display_name":"Sachit Rao","orcid":"https://orcid.org/0000-0002-6188-5290"},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sachit Rao","raw_affiliation_strings":["International Institute of Information Technology Bangalore (IIIT-B), Bangalore, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Bangalore (IIIT-B), Bangalore, India","institution_ids":["https://openalex.org/I181514455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5008362246"],"corresponding_institution_ids":["https://openalex.org/I181514455"],"apc_list":null,"apc_paid":null,"fwci":0.1326,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54367227,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"338","issue":null,"first_page":"1","last_page":"5"},"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":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech 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":0.8275916576385498},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7033489346504211},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5577173233032227},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5547901391983032},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5328092575073242},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.47592929005622864},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.4736712574958801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.466228723526001},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4289705157279968},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4221770465373993},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4146319627761841},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37437427043914795},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.23673796653747559},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17448773980140686}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8275916576385498},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7033489346504211},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5577173233032227},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5547901391983032},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5328092575073242},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.47592929005622864},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.4736712574958801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.466228723526001},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4289705157279968},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4221770465373993},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4146319627761841},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37437427043914795},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.23673796653747559},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17448773980140686},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/spcom50965.2020.9179519","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom50965.2020.9179519","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Signal Processing and Communications (SPCOM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W385466589","https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W2158131535","https://openalex.org/W2293634267","https://openalex.org/W2327501763","https://openalex.org/W2759710969","https://openalex.org/W2766219058","https://openalex.org/W2799800213","https://openalex.org/W2942807473","https://openalex.org/W2944255943","https://openalex.org/W2949573729","https://openalex.org/W2962780374","https://openalex.org/W2963403868","https://openalex.org/W2963677766","https://openalex.org/W2964089206","https://openalex.org/W2964325005","https://openalex.org/W2970045405","https://openalex.org/W3103005696","https://openalex.org/W4385245566","https://openalex.org/W6600284362","https://openalex.org/W6621543089","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6682962330","https://openalex.org/W6696934422","https://openalex.org/W6738279954","https://openalex.org/W6739901393","https://openalex.org/W6744680348","https://openalex.org/W6756138707"],"related_works":["https://openalex.org/W2076210937","https://openalex.org/W3124359860","https://openalex.org/W3134920593","https://openalex.org/W2153098279","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W36113703"],"abstract_inverted_index":{"End-to-end":[0],"Automatic":[1],"Speech":[2],"Recognition":[3],"(ASR)":[4],"models":[5,19],"with":[6,34,102],"attention,":[7,107],"especially":[8],"the":[9,35,42,48,72,78,82,103,116,140,146],"Joint":[10],"Connectionist":[11],"Temporal":[12],"Classification":[13],"(CTC)":[14],"and":[15,28,50,85,90,108,124,135],"Attention":[16,29,51],"in":[17,86,113,121],"Encoder-Decoder":[18],"have":[20],"shown":[21],"promising":[22],"results.":[23],"In":[24,54],"this":[25,55],"joint":[26],"CTC":[27,49],"framework,":[30],"misalignment":[31],"of":[32,81,99,105],"attention":[33],"ground":[36],"truth":[37],"is":[38,44,64,68],"not":[39],"penalised,":[40],"as":[41],"focus":[43],"on":[45,130],"optimising":[46],"only":[47],"cost":[52],"functions.":[53],"paper,":[56],"a":[57,96,149],"function":[58,67],"that":[59,112],"additionally":[60],"minimizes":[61],"alignment":[62,89],"errors":[63],"introduced.":[65],"This":[66],"expected":[69],"to":[70,75,77],"enable":[71],"ASR":[73],"system":[74],"attend":[76],"right":[79],"part":[80],"input":[83],"sequence,":[84],"turn,":[87],"minimize":[88],"transcription":[91],"errors.":[92],"We":[93,110,127],"also":[94],"implement":[95],"dynamic":[97],"weighting":[98],"losses":[100],"corresponding":[101],"tasks":[104],"CTC,":[106],"alignment.":[109],"demonstrate":[111],"many":[114],"cases,":[115],"proposed":[117],"design":[118],"framework":[119],"results":[120,129],"better":[122],"performance":[123],"faster":[125],"convergence.":[126],"show":[128],"two":[131],"datasets":[132],"-":[133],"TIMIT":[134],"Librispeech":[136],"100":[137],"hours":[138],"for":[139],"phone":[141],"recognition":[142],"task":[143],"by":[144],"taking":[145],"alignments":[147],"from":[148],"previously":[150],"trained":[151],"monophone":[152],"Gaussian":[153],"Mixture":[154],"Model-Hidden":[155],"Markov":[156],"Model":[157],"(GMM-HMM)":[158],"model.":[159]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
