{"id":"https://openalex.org/W4415821656","doi":"https://doi.org/10.1109/ro-man63969.2025.11217842","title":"LatentSpeech: Latent Diffusion for Text-To-Speech Generation","display_name":"LatentSpeech: Latent Diffusion for Text-To-Speech Generation","publication_year":2025,"publication_date":"2025-08-25","ids":{"openalex":"https://openalex.org/W4415821656","doi":"https://doi.org/10.1109/ro-man63969.2025.11217842"},"language":null,"primary_location":{"id":"doi:10.1109/ro-man63969.2025.11217842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man63969.2025.11217842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","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/A5035505386","display_name":"Haowei Lou","orcid":"https://orcid.org/0009-0009-1359-872X"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Haowei Lou","raw_affiliation_strings":["UNSW Sydney,School of Computer Science and Engineering,Australia,2033"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNSW Sydney,School of Computer Science and Engineering,Australia,2033","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018724341","display_name":"Hye-Young Paik","orcid":"https://orcid.org/0000-0003-4425-7388"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hye-Young Paik","raw_affiliation_strings":["UNSW Sydney,School of Computer Science and Engineering,Australia,2033"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNSW Sydney,School of Computer Science and Engineering,Australia,2033","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083611508","display_name":"Pari Delir Haghighi","orcid":"https://orcid.org/0000-0001-9922-1214"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Pari Delir Haghighi","raw_affiliation_strings":["Monash University,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University,Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["Institute of Science Tokyo,School of Engineering,Yokohama,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo,School of Engineering,Yokohama,Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074406685","display_name":"Wenhao Hu","orcid":"https://orcid.org/0000-0003-1511-2614"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wen Hu","raw_affiliation_strings":["UNSW Sydney,School of Computer Science and Engineering,Australia,2033"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNSW Sydney,School of Computer Science and Engineering,Australia,2033","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052731721","display_name":"Lina Yao","orcid":"https://orcid.org/0000-0002-4149-839X"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lina Yao","raw_affiliation_strings":["UNSW Sydney,School of Computer Science and Engineering,Australia,2033"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNSW Sydney,School of Computer Science and Engineering,Australia,2033","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28445912,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"537","last_page":"543"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.28679999709129333,"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":0.28679999709129333,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1362999975681305,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1251000016927719,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/inference","display_name":"Inference","score":0.7049999833106995},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.48249998688697815},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.46959999203681946},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.45750001072883606},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.43389999866485596},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.40400001406669617},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4004000127315521},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.39890000224113464}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7049999833106995},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.696399986743927},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.48249998688697815},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.46959999203681946},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45750001072883606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44279998540878296},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.43389999866485596},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.40400001406669617},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4004000127315521},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.39890000224113464},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3698999881744385},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.29510000348091125},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2924000024795532},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C73586568","wikidata":"https://www.wikidata.org/wiki/Q2600211","display_name":"Parameter space","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26759999990463257},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2667999863624573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ro-man63969.2025.11217842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man63969.2025.11217842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2172065531","https://openalex.org/W2963300588","https://openalex.org/W2963609956","https://openalex.org/W3096831136","https://openalex.org/W4312933868","https://openalex.org/W4375869198","https://openalex.org/W4385800847","https://openalex.org/W4405874014"],"related_works":[],"abstract_inverted_index":{"Text-To-Speech":[0],"(TTS)":[1],"generation":[2],"plays":[3],"a":[4,35,93,102,146],"crucial":[5],"role":[6],"in":[7,42,53,101],"human-robot":[8,206],"interaction":[9],"by":[10,58,164,169],"allowing":[11],"robots":[12],"to":[13,24,64,75,81,172],"communicate":[14],"naturally":[15],"with":[16,77],"humans.":[17],"Researchers":[18],"have":[19,32],"developed":[20],"various":[21],"TTS":[22,54,96,201],"models":[23,31,74,210],"enhance":[25],"speech":[26,130],"generation.":[27,49],"More":[28],"recently,":[29],"diffusion":[30,73,174],"emerged":[33],"as":[34,45,197],"powerful":[36],"generative":[37],"framework,":[38],"achieving":[39],"state-of-the-art":[40],"performance":[41],"tasks":[43],"such":[44],"image":[46],"and":[47,111,149,154,166,184,205,209],"video":[48],"However,":[50],"their":[51,65],"application":[52],"has":[55,71],"been":[56],"limited":[57],"its":[59],"slow":[60],"inference":[61,155,162],"speeds":[62],"due":[63],"iterative":[66],"denoising":[67],"process.":[68],"Previous":[69],"work":[70],"applied":[72],"Mel-Spectrograms":[76],"an":[78,119,198],"additional":[79],"vocoder":[80,148],"convert":[82],"them":[83],"into":[84,131],"waveforms.":[85],"To":[86],"address":[87],"these":[88],"limitations,":[89],"we":[90,117],"propose":[91],"LatentSpeech,":[92],"novel":[94],"diffusion-based":[95],"framework":[97],"that":[98],"operates":[99],"directly":[100],"latent":[103,121],"space.":[104],"This":[105],"space":[106,122],"is":[107],"significantly":[108],"more":[109],"compact":[110],"information-rich":[112],"than":[113],"raw":[114],"Mel-Spectrograms.":[115],"Furthermore,":[116],"introduce":[118],"alternative":[120],"of":[123],"Pseudo-Quadrature":[124],"Mirror":[125],"Filters":[126],"(PQMF),":[127],"which":[128],"decomposes":[129],"multiple":[132],"subbands.":[133],"By":[134],"leveraging":[135],"PQMF\u2019s":[136],"near-perfect":[137],"waveform":[138],"reconstruction":[139],"capability,":[140],"LatentSpeech":[141,159,196],"eliminates":[142],"the":[143,189],"need":[144],"for":[145,203],"separate":[147],"reduces":[150,161],"both":[151],"model":[152,160,167],"size":[153,168],"time.":[156],"Our":[157],"PQMF-based":[158],"time":[163],"45%":[165],"77%":[170],"compared":[171],"Mel-Spectrogram":[173],"models.":[175],"On":[176],"benchmark":[177],"datasets,":[178],"it":[179],"achieves":[180],"25%":[181],"lower":[182],"WER":[183],"58%":[185],"higher":[186],"MOS":[187],"using":[188],"same":[190],"training":[191],"data.":[192],"These":[193],"results":[194],"highlight":[195],"efficient,":[199],"high-quality":[200],"solution":[202],"real-time":[204],"interaction.":[207],"Code":[208],"are":[211],"available":[212],"here.":[213]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-03T00:00:00"}