{"id":"https://openalex.org/W4297841232","doi":"https://doi.org/10.21437/interspeech.2022-304","title":"Speaker consistency loss and step-wise optimization for semi-supervised joint training of TTS and ASR using unpaired text data","display_name":"Speaker consistency loss and step-wise optimization for semi-supervised joint training of TTS and ASR using unpaired text data","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841232","doi":"https://doi.org/10.21437/interspeech.2022-304"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-304","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-304","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5082466886","display_name":"Naoki Makishima","orcid":"https://orcid.org/0000-0002-7065-315X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Naoki Makishima","raw_affiliation_strings":["NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027868267","display_name":"Satoshi Suzuki","orcid":"https://orcid.org/0000-0001-5343-4660"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Suzuki","raw_affiliation_strings":["NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103279502","display_name":"Atsushi Ando","orcid":"https://orcid.org/0000-0003-1586-0356"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Ando","raw_affiliation_strings":["NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082466886"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.6236,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.67620125,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"526","last_page":"530"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9947999715805054,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9908999800682068,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.7418690919876099},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7353367805480957},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7353150844573975},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6628503799438477},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5556537508964539},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5423792600631714},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4291660487651825},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3988454043865204},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1089092493057251}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7418690919876099},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7353367805480957},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7353150844573975},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6628503799438477},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5556537508964539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5423792600631714},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4291660487651825},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3988454043865204},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1089092493057251},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-304","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-304","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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":28,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W773905565","https://openalex.org/W1522301498","https://openalex.org/W2012086895","https://openalex.org/W2107860279","https://openalex.org/W2546938941","https://openalex.org/W2747874407","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2888779557","https://openalex.org/W2892009249","https://openalex.org/W2903739847","https://openalex.org/W2936774411","https://openalex.org/W2938947737","https://openalex.org/W2952711665","https://openalex.org/W2963240019","https://openalex.org/W2963739817","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W3008480565","https://openalex.org/W3033411150","https://openalex.org/W3047866127","https://openalex.org/W3096086473","https://openalex.org/W3161143478","https://openalex.org/W3161704465","https://openalex.org/W3161890269","https://openalex.org/W3197324626","https://openalex.org/W4288265053"],"related_works":["https://openalex.org/W1996130883","https://openalex.org/W2748574964","https://openalex.org/W1603736412","https://openalex.org/W2888483922","https://openalex.org/W4304185162","https://openalex.org/W4396737233","https://openalex.org/W2061685118","https://openalex.org/W3006282800","https://openalex.org/W2462100143","https://openalex.org/W2367747139"],"abstract_inverted_index":{"In":[0],"this":[1,121],"paper,":[2],"we":[3,123,158],"investigate":[4],"the":[5,41,45,58,62,65,78,84,88,92,99,109,116,126,141,145,152,155,161,164,176,180,185,188],"semi-supervised":[6],"joint":[7],"training":[8,128],"of":[9,23,30,87,144,151,163,175,187],"text":[10,32,52,63],"to":[11,102,149,172,179],"speech":[12,16,50,56,80,90,94,147],"(TTS)":[13],"and":[14,26,57,91,134],"automatic":[15],"recognition":[17],"(ASR),":[18],"where":[19,44],"a":[20,27,38,54,75,130],"small":[21],"amount":[22,29],"paired":[24],"data":[25,33],"large":[28],"unpaired":[31],"are":[34,72,170],"available.Conventional":[35],"studies":[36],"form":[37],"cycle":[39],"called":[40],"TTS-ASR":[42],"pipeline,":[43],"multispeaker":[46],"TTS":[47,110,165,177],"model":[48,60,101,111,118,166,178],"synthesizes":[49],"from":[51,64],"with":[53,74,129],"reference":[55,89,153],"ASR":[59,100,117,181],"reconstructs":[61],"synthesized":[66,79,93,146],"speech,":[67],"after":[68,104],"which":[69],"both":[70,168],"models":[71,169],"trained":[73,171],"cycle-consistency":[76],"loss.However,":[77],"does":[81],"not":[82,106],"reflect":[83],"speaker":[85,131,137,142],"characteristics":[86,143],"becomes":[95],"overly":[96],"easy":[97],"for":[98],"recognize":[103],"training.This":[105],"only":[107],"decreases":[108],"quality":[112],"but":[113],"also":[114],"limits":[115],"improvement.To":[119],"solve":[120],"problem,":[122],"propose":[124],"improving":[125],"cycleconsistency-based":[127],"consistency":[132,138],"loss":[133,139],"step-wise":[135,156],"optimization.The":[136],"brings":[140],"closer":[148],"that":[150],"speech.In":[154],"optimization,":[157],"first":[159],"freeze":[160],"parameter":[162],"before":[167],"avoid":[173],"over-adaptation":[174],"model.Experimental":[182],"results":[183],"demonstrate":[184],"efficacy":[186],"proposed":[189],"method.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}