{"id":"https://openalex.org/W4375868859","doi":"https://doi.org/10.1109/icassp49357.2023.10096905","title":"M<sup>2</sup>-CTTS: End-to-End Multi-Scale Multi-Modal Conversational Text-to-Speech Synthesis","display_name":"M<sup>2</sup>-CTTS: End-to-End Multi-Scale Multi-Modal Conversational Text-to-Speech Synthesis","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868859","doi":"https://doi.org/10.1109/icassp49357.2023.10096905"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096905","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":["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/A5033565985","display_name":"Jinlong Xue","orcid":"https://orcid.org/0009-0000-0442-0932"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinlong Xue","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008597430","display_name":"Yayue Deng","orcid":"https://orcid.org/0009-0003-7642-4942"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yayue Deng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101419335","display_name":"Fengping Wang","orcid":"https://orcid.org/0009-0001-4420-4553"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengping Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343662","display_name":"Ya Li","orcid":"https://orcid.org/0000-0002-6284-5039"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033063238","display_name":"Yingming Gao","orcid":"https://orcid.org/0000-0001-5881-3723"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingming Gao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["Chinese Academy of Sciences,NLPR, Institute of Automation,Beijing,China","NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,NLPR, Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113103312","display_name":"Jianqing Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianqing Sun","raw_affiliation_strings":["Unisound AI Technology Co., Ltd,Beijing,China","Unisound AI Technology Co., Ltd, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unisound AI Technology Co., Ltd,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Unisound AI Technology Co., Ltd, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110832899","display_name":"Jiaen Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaen Liang","raw_affiliation_strings":["Unisound AI Technology Co., Ltd,Beijing,China","Unisound AI Technology Co., Ltd, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unisound AI Technology Co., Ltd,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Unisound AI Technology Co., Ltd, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1211,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.89553791,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"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/T12031","display_name":"Speech and dialogue systems","score":0.9986000061035156,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9983000159263611,"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/prosody","display_name":"Prosody","score":0.9187893867492676},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8886295557022095},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.8009251952171326},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7523833513259888},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6582226753234863},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5582185983657837},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5423714518547058},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5113167762756348},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4997975826263428},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48097455501556396},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4277370572090149},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40360474586486816},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2089238166809082},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07982471585273743},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06019982695579529}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9187893867492676},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8886295557022095},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.8009251952171326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7523833513259888},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6582226753234863},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5582185983657837},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5423714518547058},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5113167762756348},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4997975826263428},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48097455501556396},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4277370572090149},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40360474586486816},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2089238166809082},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07982471585273743},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06019982695579529},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096905","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326873","display_name":"National Laboratory of Pattern Recognition","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2747874407","https://openalex.org/W2761590056","https://openalex.org/W2896457183","https://openalex.org/W2943767081","https://openalex.org/W2964138190","https://openalex.org/W2970641574","https://openalex.org/W3033411150","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3151309757","https://openalex.org/W3196001064","https://openalex.org/W3198152857","https://openalex.org/W3206725777","https://openalex.org/W4210777104","https://openalex.org/W4225300652","https://openalex.org/W4372260474","https://openalex.org/W6745297980","https://openalex.org/W6749555683","https://openalex.org/W6750489868","https://openalex.org/W6755207826","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6795807602","https://openalex.org/W6802591955"],"related_works":["https://openalex.org/W566641833","https://openalex.org/W4392904630","https://openalex.org/W169399214","https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W2108985546"],"abstract_inverted_index":{"Conversational":[0],"text-to-speech":[1,86],"(TTS)":[2],"aims":[3],"to":[4,23,59,89],"synthesize":[5],"speech":[6],"with":[7,111,124],"proper":[8],"prosody":[9,44,71,135],"of":[10,31],"reply":[11],"based":[12],"on":[13,37],"the":[14,26,62],"historical":[15,92],"conversation.":[16],"However,":[17],"it":[18,56],"is":[19,57],"still":[20],"a":[21,29,102],"challenge":[22],"comprehensively":[24,90],"model":[25,122],"conversation,":[27],"and":[28,41,53,65,94,106,114,128,137],"majority":[30],"conversational":[32,85],"TTS":[33],"systems":[34],"only":[35,60],"focus":[36],"extracting":[38],"global":[39],"information":[40,50,127],"omit":[42],"local":[43],"features,":[45,64],"which":[46],"contain":[47,69],"important":[48],"fine-grained":[49,115,125],"like":[51],"keywords":[52],"emphasis.":[54],"Moreover,":[55],"insufficient":[58],"consider":[61],"textual":[63,103],"acoustic":[66,108,131],"features":[67,132],"also":[68],"various":[70],"information.":[72],"Hence,":[73],"we":[74,100],"propose":[75],"M":[76],"<sup":[77],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[78],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[79],"-CTTS,":[80],"an":[81,107],"end-to-end":[82],"multi-scale":[83],"multi-modal":[84],"system,":[87],"aiming":[88],"utilize":[91],"conversation":[93],"enhance":[95],"prosodic":[96],"expression.":[97],"More":[98],"specifically,":[99],"design":[101],"context":[104,109,126],"module":[105,110],"both":[112],"coarse-grained":[113],"modeling.":[116],"Experimental":[117],"results":[118],"demonstrate":[119],"that":[120],"our":[121],"mixed":[123],"additionally":[129],"considering":[130],"achieves":[133],"better":[134],"performance":[136],"naturalness":[138],"in":[139],"CMOS":[140],"tests.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}