{"id":"https://openalex.org/W4408345868","doi":"https://doi.org/10.1109/icassp49660.2025.10890208","title":"DiffCSS: Diverse and Expressive Conversational Speech Synthesis with Diffusion Models","display_name":"DiffCSS: Diverse and Expressive Conversational Speech Synthesis with Diffusion Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345868","doi":"https://doi.org/10.1109/icassp49660.2025.10890208"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890208","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/A5113820804","display_name":"Weihao Wu","orcid":"https://orcid.org/0009-0006-4466-1080"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihao Wu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102424493","display_name":"Zhiwei Lin","orcid":"https://orcid.org/0000-0003-0389-4444"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Lin","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089348821","display_name":"Yixuan Zhou","orcid":"https://orcid.org/0000-0003-4984-2252"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixuan Zhou","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084724046","display_name":"Jingbei Li","orcid":"https://orcid.org/0000-0003-4823-0131"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingbei Li","raw_affiliation_strings":["StepFun"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"StepFun","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010655034","display_name":"Rui Niu","orcid":"https://orcid.org/0000-0002-8599-6374"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Niu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016939864","display_name":"Qinghua Wu","orcid":"https://orcid.org/0000-0002-0598-8367"},"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":"Qinghua Wu","raw_affiliation_strings":["Tencent Youtu Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050836381","display_name":"Songjun Cao","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":"Songjun Cao","raw_affiliation_strings":["Tencent Youtu Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037377300","display_name":"Long Ma","orcid":"https://orcid.org/0000-0001-5125-0198"},"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":"Long Ma","raw_affiliation_strings":["Tencent Youtu Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111019783","display_name":"Zhiyong Wu","orcid":null},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.346,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90271037,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"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":0.9822999835014343,"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":0.9822999835014343,"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":0.7563056945800781},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5981019735336304},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5390043258666992},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.446217805147171},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33239293098449707},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.052910178899765015}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7563056945800781},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5981019735336304},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5390043258666992},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.446217805147171},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33239293098449707},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.052910178899765015},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890208","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":0.4399999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W3151309757","https://openalex.org/W3194782062","https://openalex.org/W3215615641","https://openalex.org/W4225300652","https://openalex.org/W4252812408","https://openalex.org/W4304013787","https://openalex.org/W4307323391","https://openalex.org/W4312933868","https://openalex.org/W4372260474","https://openalex.org/W4375868859","https://openalex.org/W4385570943","https://openalex.org/W4385823191","https://openalex.org/W4392902952","https://openalex.org/W4403780722","https://openalex.org/W6751990271","https://openalex.org/W6769627184","https://openalex.org/W6778823374","https://openalex.org/W6778883912","https://openalex.org/W6779823529","https://openalex.org/W6788990321","https://openalex.org/W6795288823","https://openalex.org/W6796464841","https://openalex.org/W6848735303","https://openalex.org/W6850334629","https://openalex.org/W6853096648","https://openalex.org/W6853515095","https://openalex.org/W6861507043","https://openalex.org/W6862144568"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Conversational":[0],"speech":[1,117,128],"synthesis":[2],"(CSS)":[3],"aims":[4],"to":[5,19,32,81,96,114],"synthesize":[6,115],"both":[7],"contextually":[8,86,134],"appropriate":[9],"and":[10,13,53,76,85,136],"expressive":[11,137],"speech,":[12],"considerable":[14],"efforts":[15],"have":[16],"been":[17],"made":[18],"enhance":[20],"the":[21,36,51,126],"understanding":[22],"of":[23,38,55],"conversational":[24,104],"context.":[25,105],"However,":[26],"existing":[27,139],"CSS":[28,70,140],"systems":[29],"are":[30],"limited":[31],"deterministic":[33],"prediction,":[34],"overlooking":[35],"diversity":[37],"potential":[39],"responses.":[40],"Moreover,":[41],"they":[42],"rarely":[43],"employ":[44],"language":[45],"model":[46],"(LM)-based":[47],"TTS":[48,79,110],"backbones,":[49],"limiting":[50],"naturalness":[52],"quality":[54],"synthesized":[56,127],"speech.":[57,88],"To":[58],"address":[59],"these":[60],"issues,":[61],"in":[62],"this":[63],"paper,":[64],"we":[65],"propose":[66],"DiffCSS,":[67],"an":[68,77],"innovative":[69],"framework":[71],"that":[72,125],"leverages":[73],"diffusion":[74],"models":[75],"LM-based":[78,109],"backbone":[80,111],"generate":[82],"diverse,":[83,133],"expressive,":[84],"coherent":[87],"A":[89],"diffusion-based":[90],"context-aware":[91],"prosody":[92,99,120],"predictor":[93],"is":[94,112,131],"proposed":[95],"sample":[97],"diverse":[98],"embeddings":[100],"conditioned":[101],"on":[102],"multimodal":[103],"Then":[106],"a":[107],"prosody-controllable":[108],"developed":[113],"high-quality":[116],"with":[118],"sampled":[119],"embeddings.":[121],"Experimental":[122],"results":[123],"demonstrate":[124],"from":[129],"DiffCSS":[130],"more":[132],"coherent,":[135],"than":[138],"systems1.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}