{"id":"https://openalex.org/W3025182306","doi":"https://doi.org/10.21437/odyssey.2020-35","title":"WaveTTS: Tacotron-based TTS with Joint Time-Frequency Domain Loss","display_name":"WaveTTS: Tacotron-based TTS with Joint Time-Frequency Domain Loss","publication_year":2020,"publication_date":"2020-05-15","ids":{"openalex":"https://openalex.org/W3025182306","doi":"https://doi.org/10.21437/odyssey.2020-35","mag":"3025182306"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2020-35","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2020-35","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2020)","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/A5082746577","display_name":"Rui Liu","orcid":"https://orcid.org/0000-0003-4524-7413"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001303929","display_name":"Berrak \u015ei\u015fman","orcid":"https://orcid.org/0000-0001-8078-3305"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Berrak Sisman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014372166","display_name":"Feilong Bao","orcid":"https://orcid.org/0000-0001-7312-1629"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feilong Bao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"245","last_page":"251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9959999918937683,"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":0.9959999918937683,"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":0.9835000038146973,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.963100016117096,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.9060331583023071},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7359810471534729},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.6668545007705688},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.6215012073516846},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.6018456220626831},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5336132049560547},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.527021050453186},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.43985801935195923},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43378353118896484},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.348554402589798},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12367522716522217},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12251809239387512},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08788657188415527},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.06104382872581482}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.9060331583023071},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7359810471534729},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.6668545007705688},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.6215012073516846},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.6018456220626831},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5336132049560547},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.527021050453186},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.43985801935195923},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43378353118896484},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.348554402589798},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12367522716522217},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12251809239387512},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08788657188415527},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.06104382872581482},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"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/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/odyssey.2020-35","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2020-35","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2020)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2039489009","https://openalex.org/W2024367938","https://openalex.org/W2782295999","https://openalex.org/W2162306796","https://openalex.org/W1970292246","https://openalex.org/W2016162169","https://openalex.org/W4247952185","https://openalex.org/W1895367623","https://openalex.org/W1642462315","https://openalex.org/W2015118744"],"abstract_inverted_index":{"Tacotron-based":[0,79],"text-to-speech":[1],"(TTS)":[2],"systems":[3],"directly":[4,59],"synthesize":[5],"speech":[6,138],"from":[7,42],"text":[8],"input.":[9],"Such":[10],"frameworks":[11],"typically":[12],"consist":[13],"of":[14,63,131,149],"a":[15,29,34,74],"feature":[16,117],"prediction":[17],"network":[18],"that":[19,37,57,85,98,112,159],"maps":[20],"character":[21],"sequences":[22],"to":[23,82],"frequency-domain":[24,54,110],"acoustic":[25,43,55,116,124,133],"features,":[26,56],"followed":[27],"by":[28],"waveform":[30,41,96],"reconstruction":[31],"algorithm":[32],"or":[33],"neural":[35],"vocoder":[36],"generates":[38],"the":[39,46,61,64,95,100,103,114,120,129,132,136,146,160,164],"time-domain":[40,66,91],"features.":[44,125],"As":[45],"loss":[47,88,118],"function":[48],"is":[49,145],"usually":[50],"calculated":[51],"only":[52],"for":[53,78],"doesn't":[58],"control":[60],"quality":[62,130],"generated":[65,106,123],"waveform.":[67,139],"To":[68,140],"address":[69],"this":[70,144],"problem,":[71],"we":[72],"propose":[73],"new":[75],"training":[76],"scheme":[77],"TTS,":[80],"referred":[81],"as":[83,94],"WaveTTS,":[84],"has":[86],"2":[87],"functions:":[89],"1)":[90],"loss,":[92,97,111],"denoted":[93],"measures":[99,113],"distortion":[101],"between":[102,119],"natural":[104,121],"and":[105,108,122,135,166],"waveform;":[107],"2)":[109],"Mel-scale":[115],"WaveTTS":[126],"ensures":[127],"both":[128],"features":[134],"resulting":[137],"our":[141],"best":[142],"knowledge,":[143],"first":[147],"implementation":[148],"Tacotron":[150],"with":[151],"joint":[152],"time-frequency":[153],"domain":[154],"loss.":[155],"Experimental":[156],"results":[157],"show":[158],"proposed":[161],"framework":[162],"outperforms":[163],"baselines":[165],"achieves":[167],"high-quality":[168],"synthesized":[169],"speech.":[170]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}