{"id":"https://openalex.org/W4392909102","doi":"https://doi.org/10.1109/icassp48485.2024.10447661","title":"DCTTS: Discrete Diffusion Model with Contrastive Learning for Text-to-Speech Generation","display_name":"DCTTS: Discrete Diffusion Model with Contrastive Learning for Text-to-Speech Generation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909102","doi":"https://doi.org/10.1109/icassp48485.2024.10447661"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5087449078","display_name":"Zhichao Wu","orcid":"https://orcid.org/0000-0002-1195-8834"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhichao Wu","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics,Nanjing,China","Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics,Nanjing,China","institution_ids":["https://openalex.org/I9842412"]},{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087333633","display_name":"Qiulin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiulin Li","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics,Nanjing,China","Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics,Nanjing,China","institution_ids":["https://openalex.org/I9842412"]},{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054891120","display_name":"Sixing Liu","orcid":"https://orcid.org/0000-0001-8181-7749"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sixing Liu","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics,Nanjing,China","Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics,Nanjing,China","institution_ids":["https://openalex.org/I9842412"]},{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022836264","display_name":"Qun Yang","orcid":"https://orcid.org/0000-0001-6824-8473"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qun Yang","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics,Nanjing,China","Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics,Nanjing,China","institution_ids":["https://openalex.org/I9842412"]},{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9842412"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11336","last_page":"11340"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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":0.9962999820709229,"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/T10860","display_name":"Speech and Audio Processing","score":0.9958000183105469,"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":0.8016178607940674},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6126041412353516},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5630738735198975},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5345755219459534},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5290184020996094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4743053913116455},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4613535404205322},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.43074965476989746},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4227473735809326},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41992273926734924},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10685718059539795},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.08484739065170288}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8016178607940674},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6126041412353516},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5630738735198975},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5345755219459534},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5290184020996094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4743053913116455},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4613535404205322},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.43074965476989746},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4227473735809326},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41992273926734924},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10685718059539795},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.08484739065170288},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W349236604","https://openalex.org/W2120847449","https://openalex.org/W2899663614","https://openalex.org/W2903739847","https://openalex.org/W2964243274","https://openalex.org/W3033411150","https://openalex.org/W3180355996","https://openalex.org/W3207498282","https://openalex.org/W4226132755","https://openalex.org/W4285605725","https://openalex.org/W4304099317","https://openalex.org/W4312388283","https://openalex.org/W4367359628","https://openalex.org/W4372266896","https://openalex.org/W4385245566","https://openalex.org/W6633684334","https://openalex.org/W6679045638","https://openalex.org/W6755977528","https://openalex.org/W6778823374","https://openalex.org/W6795261426","https://openalex.org/W6802805937","https://openalex.org/W6838582276","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2381850946","https://openalex.org/W4380449851","https://openalex.org/W3125091513","https://openalex.org/W4318832338","https://openalex.org/W3162204513","https://openalex.org/W4248383205","https://openalex.org/W4234745530","https://openalex.org/W2146383839","https://openalex.org/W4390516098","https://openalex.org/W2231829109"],"abstract_inverted_index":{"In":[0,73],"the":[1,4,34,54,66,70,77,94,104,121],"Text-to-speech(TTS)":[2],"task,":[3],"latent":[5],"diffusion":[6,67,80,95,125],"model":[7,68,96],"has":[8,110],"excellent":[9],"fidelity":[10],"and":[11,18,49,63,115],"generalization,":[12],"but":[13],"its":[14],"expensive":[15],"resource":[16,122],"consumption":[17,123],"slow":[19],"inference":[20],"speed":[21,117],"have":[22],"always":[23],"been":[24],"a":[25,47,89],"challenging.":[26],"To":[27],"address":[28],"this":[29,31,108],"issue,":[30],"paper":[32,109],"proposes":[33],"Discrete":[35],"Diffusion":[36],"Model":[37],"with":[38],"Contrastive":[39],"Learning":[40],"for":[41],"Text-to-Speech":[42],"Generation(DCTTS).":[43],"Specifically,":[44],"we":[45,87],"employs":[46],"straightforward":[48],"effective":[50],"text":[51],"encoder,":[52],"compresses":[53],"raw":[55],"data":[56],"into":[57],"discrete":[58,71],"space":[59],"using":[60],"VQ":[61],"model,":[62],"then":[64],"trains":[65],"on":[69],"space.":[72],"order":[74],"to":[75,83],"minimize":[76],"number":[78],"of":[79,124],"steps":[81],"needed":[82],"synthesis":[84,113],"high-quality":[85],"speech,":[86],"used":[88],"contrastive":[90],"learning":[91],"loss":[92],"throughout":[93],"training":[97],"phase.":[98],"The":[99,127],"experimental":[100],"results":[101],"demonstrate":[102],"that":[103],"approach":[105],"proposed":[106],"in":[107],"outstanding":[111],"speech":[112],"quality":[114],"sampling":[116],"while":[118],"significantly":[119],"reducing":[120],"model.":[126],"synthesized":[128],"samples":[129],"are":[130],"available":[131],"at":[132],"https://github.com/lawtherWu/DCTTS":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}