{"id":"https://openalex.org/W4402112155","doi":"https://doi.org/10.21437/interspeech.2024-335","title":"Improving Robustness of LLM-based Speech Synthesis by Learning Monotonic Alignment","display_name":"Improving Robustness of LLM-based Speech Synthesis by Learning Monotonic Alignment","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112155","doi":"https://doi.org/10.21437/interspeech.2024-335"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-335","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-335","pdf_url":"https://www.isca-archive.org/interspeech_2024/neekhara24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2024/neekhara24_interspeech.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030710635","display_name":"Paarth Neekhara","orcid":"https://orcid.org/0009-0002-8598-0353"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Paarth Neekhara","raw_affiliation_strings":["NVIDIA Corporation , Santa Clara , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation , Santa Clara , CA , USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015232966","display_name":"Shehzeen Hussain","orcid":"https://orcid.org/0000-0003-4693-2113"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shehzeen Hussain","raw_affiliation_strings":["NVIDIA Corporation , Santa Clara , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation , Santa Clara , CA , USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101935896","display_name":"Subhankar Ghosh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Subhankar Ghosh","raw_affiliation_strings":["NVIDIA Corporation , Santa Clara , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation , Santa Clara , CA , USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100762970","display_name":"Jason Li","orcid":"https://orcid.org/0000-0002-1150-3549"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Li","raw_affiliation_strings":["NVIDIA Corporation , Santa Clara , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation , Santa Clara , CA , USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032957280","display_name":"Boris Ginsburg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":["NVIDIA Corporation , Santa Clara , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation , Santa Clara , CA , USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5030710635"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":2.5799,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90945161,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3425","last_page":"3429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9836000204086304,"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":0.9836000204086304,"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":0.9236000180244446,"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":0.9049999713897705,"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/robustness","display_name":"Robustness (evolution)","score":0.7966787815093994},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6795821189880371},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.4871253967285156},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42228686809539795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4102162718772888},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11900126934051514}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7966787815093994},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6795821189880371},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.4871253967285156},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42228686809539795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4102162718772888},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11900126934051514},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-335","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-335","pdf_url":"https://www.isca-archive.org/interspeech_2024/neekhara24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2024-335","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-335","pdf_url":"https://www.isca-archive.org/interspeech_2024/neekhara24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402112155.pdf","grobid_xml":"https://content.openalex.org/works/W4402112155.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2077314575","https://openalex.org/W4315701745","https://openalex.org/W1990290471","https://openalex.org/W4380682190","https://openalex.org/W2005710836","https://openalex.org/W2102386043","https://openalex.org/W2945307361","https://openalex.org/W2116636209"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Model":[2],"(LLM)":[3],"based":[4],"text-to-speech":[5],"(TTS)":[6],"systems":[7],"have":[8],"demonstrated":[9],"remarkable":[10],"capabilities":[11],"in":[12,64,75],"handling":[13],"large":[14],"speech":[15,20,42,83,89],"datasets":[16],"and":[17,40,69,82,106,128],"generating":[18],"natural":[19],"for":[21,87,91],"new":[22,125],"speakers.However,":[23],"LLM-based":[24,133],"TTS":[25,134],"models":[26,77],"are":[27],"not":[28,122],"robust":[29],"as":[30,45],"the":[31,52,58,80,96,114],"generated":[32],"output":[33],"can":[34],"contain":[35],"repeating":[36],"words,":[37],"missing":[38],"words":[39],"mis-aligned":[41],"(referred":[43],"to":[44],"hallucinations":[46],"or":[47],"attention":[48,107,118],"errors),":[49],"especially":[50],"when":[51,85],"text":[53,81,115],"contains":[54],"multiple":[55],"occurrences":[56],"of":[57,132],"same":[59],"token.We":[60],"examine":[61],"these":[62],"challenges":[63],"an":[65],"encoder-decoder":[66],"transformer":[67],"model":[68],"find":[70],"that":[71,109],"certain":[72],"cross-attention":[73,112],"heads":[74],"such":[76],"implicitly":[78],"learn":[79],"alignment":[84,97],"trained":[86],"predicting":[88],"tokens":[90],"a":[92],"given":[93],"text.To":[94],"make":[95],"more":[98],"robust,":[99],"we":[100],"propose":[101],"techniques":[102],"utilizing":[103],"CTC":[104],"loss":[105],"priors":[108],"encourage":[110],"monotonic":[111],"over":[113],"tokens.Our":[116],"guided":[117],"training":[119],"technique":[120],"does":[121],"introduce":[123],"any":[124],"learnable":[126],"parameters":[127],"significantly":[129],"improves":[130],"robustness":[131],"models.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4}],"updated_date":"2026-05-09T13:55:54.758798","created_date":"2025-10-10T00:00:00"}