{"id":"https://openalex.org/W4408355874","doi":"https://doi.org/10.1109/icassp49660.2025.10890055","title":"Enabling Beam Search for Language Model-Based Text-to-Speech Synthesis","display_name":"Enabling Beam Search for Language Model-Based Text-to-Speech Synthesis","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355874","doi":"https://doi.org/10.1109/icassp49660.2025.10890055"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5051713582","display_name":"Zehai Tu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehai Tu","raw_affiliation_strings":["LightSpeed Studios, Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LightSpeed Studios, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102854878","display_name":"Guangyan Zhang","orcid":"https://orcid.org/0000-0002-3480-5902"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyan Zhang","raw_affiliation_strings":["LightSpeed Studios, Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LightSpeed Studios, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009680990","display_name":"Yiting Lu","orcid":"https://orcid.org/0000-0002-7615-4167"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiting Lu","raw_affiliation_strings":["LightSpeed Studios, Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LightSpeed Studios, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053310461","display_name":"Adaeze Adigwe","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Adaeze Adigwe","raw_affiliation_strings":["University of Edinburgh,The Centre for Speech Technology Research,Edinburgh,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,The Centre for Speech Technology Research,Edinburgh,UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101826175","display_name":"Simon King","orcid":"https://orcid.org/0000-0001-6769-5757"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["University of Edinburgh,The Centre for Speech Technology Research,Edinburgh,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,The Centre for Speech Technology Research,Edinburgh,UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067005644","display_name":"Yiwen Guo","orcid":"https://orcid.org/0000-0002-0709-4877"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwen Guo","raw_affiliation_strings":["LightSpeed Studios, Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LightSpeed Studios, Tencent","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"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":0.9839000105857849,"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":0.9839000105857849,"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":0.9781000018119812,"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":0.9581999778747559,"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/computer-science","display_name":"Computer science","score":0.7995055913925171},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6245802640914917},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5693684220314026},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5108366012573242},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4603523910045624},{"id":"https://openalex.org/keywords/beam-search","display_name":"Beam search","score":0.4141945242881775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4069986939430237},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19181609153747559},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.1291828453540802}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7995055913925171},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6245802640914917},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5693684220314026},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5108366012573242},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4603523910045624},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.4141945242881775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4069986939430237},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19181609153747559},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.1291828453540802}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2890964092","https://openalex.org/W2972359262","https://openalex.org/W2995969307","https://openalex.org/W3163132306","https://openalex.org/W3198533616","https://openalex.org/W3198694222","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3215615641","https://openalex.org/W4283067311","https://openalex.org/W4307323391","https://openalex.org/W4381786045","https://openalex.org/W4385823321","https://openalex.org/W4390075359","https://openalex.org/W4391833199","https://openalex.org/W4392931276","https://openalex.org/W4402112533","https://openalex.org/W4402672020","https://openalex.org/W4406417959","https://openalex.org/W6728274705","https://openalex.org/W6729900021","https://openalex.org/W6761551260","https://openalex.org/W6771467084","https://openalex.org/W6790356757","https://openalex.org/W6847363464","https://openalex.org/W6848735303","https://openalex.org/W6861507043","https://openalex.org/W6869301554","https://openalex.org/W6870225445"],"related_works":["https://openalex.org/W4386269615","https://openalex.org/W3156736277","https://openalex.org/W4390091683","https://openalex.org/W2100233978","https://openalex.org/W2204575588","https://openalex.org/W4287332007","https://openalex.org/W58921990","https://openalex.org/W3128265108","https://openalex.org/W2114916462","https://openalex.org/W3127565211"],"abstract_inverted_index":{"Tokenising":[0],"continuous":[1],"speech":[2,29,96,113],"into":[3],"sequences":[4,92],"of":[5,62,69,93],"discrete":[6],"tokens":[7],"and":[8,33,78,117],"modelling":[9],"them":[10],"with":[11,30,99,114],"language":[12],"models":[13,26,104],"(LMs)":[14],"has":[15],"led":[16],"to":[17,87],"significant":[18],"success":[19],"in":[20],"text-to-speech":[21],"(TTS)":[22],"synthesis.":[23],"Despite":[24],"these":[25,52],"can":[27,38],"generate":[28],"high":[31],"quality":[32],"naturalness,":[34],"their":[35],"synthesised":[36],"samples":[37],"still":[39],"suffer":[40],"from":[41],"artefacts,":[42],"mispronunciation,":[43],"word":[44],"repeating,":[45],"etc.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50,72],"argue":[51],"undesirable":[53],"properties":[54],"could":[55],"partly":[56],"be":[57],"caused":[58],"by":[59],"the":[60,66,89,94],"randomness":[61],"sampling-based":[63],"strategies":[64],"during":[65],"autoregressive":[67],"decoding":[68,76,110],"LMs.":[70],"Therefore,":[71],"look":[73],"at":[74],"maximization-based":[75],"approaches":[77],"propose":[79],"Temporal":[80],"Repetition":[81],"Aware":[82],"Diverse":[83],"Beam":[84],"Search":[85],"(TRAD-BS)":[86],"find":[88],"most":[90],"probable":[91],"generated":[95],"tokens.":[97],"Experiments":[98],"two":[100],"recent":[101],"LM-based":[102],"TTS":[103],"demonstrate":[105],"that":[106],"our":[107],"proposed":[108],"maximisation-based":[109],"strategy":[111],"generates":[112],"fewer":[115],"mispronunciations":[116],"improved":[118],"speaker":[119],"consistency<sup":[120],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[121],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}