{"id":"https://openalex.org/W4372260261","doi":"https://doi.org/10.1109/icassp49357.2023.10096710","title":"LightGrad: Lightweight Diffusion Probabilistic Model for Text-to-Speech","display_name":"LightGrad: Lightweight Diffusion Probabilistic Model for Text-to-Speech","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260261","doi":"https://doi.org/10.1109/icassp49357.2023.10096710"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096710","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.16569","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100332831","display_name":"Jie Chen","orcid":"https://orcid.org/0000-0001-6474-9238"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jie Chen","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074833963","display_name":"Xingchen Song","orcid":"https://orcid.org/0009-0009-9516-5361"},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingchen Song","raw_affiliation_strings":["Horizon Robotics,Beijing,China","Horizon Robotics, Beijing, China","WeNet Open Source Community"],"affiliations":[{"raw_affiliation_string":"Horizon Robotics,Beijing,China","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"Horizon Robotics, Beijing, China","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041630666","display_name":"Zhendong Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhendong Peng","raw_affiliation_strings":["Horizon Robotics,Beijing,China","Horizon Robotics, Beijing, China","WeNet Open Source Community"],"affiliations":[{"raw_affiliation_string":"Horizon Robotics,Beijing,China","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"Horizon Robotics, Beijing, China","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449716","display_name":"Binbin Zhang","orcid":"https://orcid.org/0000-0002-7164-5127"},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binbin Zhang","raw_affiliation_strings":["Horizon Robotics,Beijing,China","WeNet Open Source Community","Horizon Robotics, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Horizon Robotics,Beijing,China","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]},{"raw_affiliation_string":"Horizon Robotics, Beijing, China","institution_ids":["https://openalex.org/I4401726824"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031150833","display_name":"Fuping Pan","orcid":"https://orcid.org/0000-0001-9171-0726"},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuping Pan","raw_affiliation_strings":["Horizon Robotics,Beijing,China","Horizon Robotics, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Horizon Robotics,Beijing,China","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"Horizon Robotics, Beijing, China","institution_ids":["https://openalex.org/I4401726824"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100332831"],"corresponding_institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.0556,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89181334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9968000054359436,"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":0.9959999918937683,"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":0.7500476837158203},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7170956134796143},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5992430448532104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47377777099609375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3695570230484009},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32996729016304016},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06368094682693481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7500476837158203},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7170956134796143},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5992430448532104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47377777099609375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3695570230484009},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32996729016304016},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06368094682693481},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096710","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2308.16569","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.16569","pdf_url":"https://arxiv.org/pdf/2308.16569","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.16569","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.16569","pdf_url":"https://arxiv.org/pdf/2308.16569","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.44999998807907104,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1888327543","display_name":null,"funder_award_id":"15001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2123497280","display_name":null,"funder_award_id":"202106","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2603945996","display_name":null,"funder_award_id":"62076144","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5898128861","display_name":null,"funder_award_id":"61405150","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4372260261.pdf"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W2129069237","https://openalex.org/W2531409750","https://openalex.org/W2903739847","https://openalex.org/W2946200149","https://openalex.org/W2963609956","https://openalex.org/W3010768098","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3036167779","https://openalex.org/W3092028330","https://openalex.org/W3095389792","https://openalex.org/W3095883095","https://openalex.org/W3095999419","https://openalex.org/W3110257065","https://openalex.org/W3120633509","https://openalex.org/W3123097577","https://openalex.org/W3129651364","https://openalex.org/W3158762648","https://openalex.org/W3160190545","https://openalex.org/W3160289600","https://openalex.org/W3160919572","https://openalex.org/W3162046328","https://openalex.org/W3162926177","https://openalex.org/W3172148458","https://openalex.org/W3198213150","https://openalex.org/W3204602440","https://openalex.org/W4225305667","https://openalex.org/W4226320669","https://openalex.org/W4281661987","https://openalex.org/W4286950013","https://openalex.org/W4288257146","https://openalex.org/W6763832098","https://openalex.org/W6771571646","https://openalex.org/W6774776664","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6779823529","https://openalex.org/W6781550413","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6784627912","https://openalex.org/W6784782250","https://openalex.org/W6786375611","https://openalex.org/W6795261426","https://openalex.org/W6795288823","https://openalex.org/W6802142237","https://openalex.org/W6802527329","https://openalex.org/W6810330366","https://openalex.org/W6838327568","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2943623134","https://openalex.org/W2494523064","https://openalex.org/W2215759665","https://openalex.org/W2030292806","https://openalex.org/W2960358116","https://openalex.org/W2938171715","https://openalex.org/W4287727129","https://openalex.org/W3041172967","https://openalex.org/W2749065928","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,19,101,144,157,161,174],"neural":[3],"text-to-speech":[4],"(TTS)":[5],"models":[6,16,28,32,68],"bring":[7],"thousands":[8],"of":[9,62],"TTS":[10,67],"applications":[11],"into":[12],"daily":[13],"life,":[14],"where":[15],"are":[17,29,40,81,88],"deployed":[18],"cloud":[20,55],"to":[21,146],"provide":[22],"services":[23],"for":[24,92,115],"customs.":[25],"Among":[26],"these":[27],"diffusion":[30,124],"probabilistic":[31],"(DPMs),":[33],"which":[34,103],"can":[35],"be":[36],"stably":[37],"trained":[38],"and":[39,53,59,126,136,172],"more":[41],"parameter-efficient":[42],"compared":[43],"with":[44,120,151],"other":[45],"generative":[46],"models.":[47],"As":[48],"transmitting":[49],"data":[50],"between":[51],"customs":[52],"the":[54,60],"introduces":[56],"high":[57],"latency":[58,148],"risk":[61],"exposing":[63],"private":[64],"data,":[65],"deploying":[66],"on":[69,168],"edge":[70,78],"devices":[71],"is":[72,118,141],"preferred.":[73],"When":[74],"implementing":[75],"DPMs":[76,87,96],"onto":[77],"devices,":[79],"there":[80],"two":[82],"practical":[83],"problems.":[84],"First,":[85],"current":[86],"not":[89],"lightweight":[90,113,122],"enough":[91],"resource-constrained":[93],"devices.":[94],"Second,":[95],"require":[97],"many":[98],"denoising":[99,176],"steps":[100,177],"inference,":[102],"increases":[104],"latency.":[105,138],"In":[106],"this":[107],"work,":[108],"we":[109],"present":[110],"LightGrad,":[111],"a":[112,121,127],"DPM":[114],"TTS.":[116],"LightGrad":[117,145,153],"equipped":[119],"U-Net":[123],"decoder":[125],"training-free":[128],"fast":[129],"sampling":[130],"technique,":[131],"reducing":[132],"both":[133,169],"model":[134],"parameters":[135],"inference":[137,140],"Streaming":[139],"also":[142],"implemented":[143],"reduce":[147],"further.":[149],"Compared":[150],"Grad-TTS,":[152],"achieves":[154],"62.2%":[155],"reduction":[156,160],"paramters,":[158],"65.7%":[159],"latency,":[162],"while":[163],"preserving":[164],"comparable":[165],"speech":[166],"quality":[167],"Chinese":[170],"Mandarin":[171],"English":[173],"4":[175],"<sup":[178],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[179],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[180],".":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}