{"id":"https://openalex.org/W3081794953","doi":"https://doi.org/10.1109/spcom50965.2020.9179603","title":"Multi-target hybrid CTC-Attentional Decoder for joint phoneme-grapheme recognition","display_name":"Multi-target hybrid CTC-Attentional Decoder for joint phoneme-grapheme recognition","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3081794953","doi":"https://doi.org/10.1109/spcom50965.2020.9179603","mag":"3081794953"},"language":"en","primary_location":{"id":"doi:10.1109/spcom50965.2020.9179603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom50965.2020.9179603","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 TechnologyBangalore (IIIT-B), Bangalore, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information TechnologyBangalore (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 TechnologyBangalore (IIIT-B), Bangalore, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information TechnologyBangalore (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 TechnologyBangalore (IIIT-B), Bangalore, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information TechnologyBangalore (IIIT-B), Bangalore, India","institution_ids":["https://openalex.org/I181514455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008362246"],"corresponding_institution_ids":["https://openalex.org/I181514455"],"apc_list":null,"apc_paid":null,"fwci":0.5412,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73871746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"2020","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9995999932289124,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8522191047668457},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.8497902750968933},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7168260812759399},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6939576268196106},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6635086536407471},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6136049628257751},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5795361399650574},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.4905704855918884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45754262804985046},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4297091066837311},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4156801998615265},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.39163222908973694},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3799296021461487},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36678752303123474},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07210472226142883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8522191047668457},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.8497902750968933},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7168260812759399},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6939576268196106},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6635086536407471},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6136049628257751},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5795361399650574},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.4905704855918884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45754262804985046},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4297091066837311},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4156801998615265},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39163222908973694},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3799296021461487},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36678752303123474},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07210472226142883},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/spcom50965.2020.9179603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom50965.2020.9179603","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"},{"id":"mag:3163183120","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002282841153917","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","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":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4099999964237213,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W308849112","https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1596367707","https://openalex.org/W1902237438","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2148450754","https://openalex.org/W2606974598","https://openalex.org/W2735006420","https://openalex.org/W2766219058","https://openalex.org/W2884254529","https://openalex.org/W2886319145","https://openalex.org/W2890197052","https://openalex.org/W2898132662","https://openalex.org/W2899879954","https://openalex.org/W2937402758","https://openalex.org/W2944255943","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2963226322","https://openalex.org/W2963303028","https://openalex.org/W2963382687","https://openalex.org/W2963403868","https://openalex.org/W2964107261","https://openalex.org/W2964308564","https://openalex.org/W2964325005","https://openalex.org/W2972426539","https://openalex.org/W2972741966","https://openalex.org/W3010788072","https://openalex.org/W3103005696","https://openalex.org/W4385245566","https://openalex.org/W6621543089","https://openalex.org/W6623517193","https://openalex.org/W6679434410","https://openalex.org/W6739901393","https://openalex.org/W6755252288"],"related_works":["https://openalex.org/W2008638795","https://openalex.org/W2155033763","https://openalex.org/W1994694193","https://openalex.org/W1990589093","https://openalex.org/W1586532344","https://openalex.org/W2058877998","https://openalex.org/W2171506966","https://openalex.org/W2225817525","https://openalex.org/W2996122240","https://openalex.org/W3100910367"],"abstract_inverted_index":{"In":[0,22],"traditional":[1],"Automatic":[2],"Speech":[3],"Recognition":[4],"(ASR)":[5],"systems,":[6],"such":[7,27,105],"as":[8,19],"HMM-based":[9],"architectures,":[10],"words":[11],"are":[12],"predicted":[13],"using":[14,31,119],"either":[15],"phonemes":[16,58],"or":[17],"graphemes":[18,60],"sub-word":[20],"units.":[21],"this":[23,129],"paper,":[24],"we":[25,117],"explore":[26],"joint":[28],"phoneme-grapheme":[29],"decoding":[30],"an":[32,95,106,131],"Encoder-Decoder":[33],"network":[34,46,70],"with":[35,128],"hybrid":[36],"Connectionist":[37],"Temporal":[38],"Classification":[39],"(CTC)":[40],"and":[41,59,68,85,100,122,140],"Attention":[42],"mechanism.":[43],"The":[44],"Encoder":[45,64,67,99],"is":[47,71],"shared":[48],"between":[49],"two":[50],"Attentional":[51],"Decoders":[52],"which":[53],"individually":[54],"learn":[55],"to":[56,77,104],"predict":[57],"from":[61],"a":[62,74],"unique":[63],"representation.":[65],"This":[66],"multi-decoder":[69],"trained":[72],"in":[73,133],"multi-task":[75],"setting":[76],"minimize":[78],"the":[79,91,120,136],"prediction":[80],"error":[81],"for":[82],"both":[83],"phoneme":[84,92,139],"grapheme":[86,141],"sequences.":[87],"We":[88],"also":[89],"implement":[90],"decoder":[93],"at":[94],"intermediate":[96],"layer":[97],"of":[98],"demonstrate":[101],"performance":[102,134],"benefits":[103],"architecture.":[107],"By":[108],"carrying":[109],"out":[110],"various":[111],"experiments":[112],"on":[113],"different":[114],"architectural":[115],"choices,":[116],"demonstrate,":[118],"TIMIT":[121],"Librispeech":[123],"100":[124],"hours":[125],"datasets,":[126],"that":[127],"approach,":[130],"improvement":[132],"than":[135],"baseline":[137],"independent":[138],"recognition":[142],"systems":[143],"can":[144],"be":[145],"achieved.":[146]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}