{"id":"https://openalex.org/W3203852729","doi":"https://doi.org/10.1109/icassp43922.2022.9747728","title":"On the Interplay between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis","display_name":"On the Interplay between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3203852729","doi":"https://doi.org/10.1109/icassp43922.2022.9747728","mag":"3203852729"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747728","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747728","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5010825170","display_name":"Cheng-I Lai","orcid":"https://orcid.org/0000-0002-2343-8596"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng-I Jeff Lai","raw_affiliation_strings":["MIT CSAIL,USA","MIT-IBM Watson AI Lab, USA","MIT CSAIL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL,USA","institution_ids":[]},{"raw_affiliation_string":"MIT-IBM Watson AI Lab, USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"MIT CSAIL, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082349516","display_name":"Erica Cooper","orcid":"https://orcid.org/0000-0002-2978-2793"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Erica Cooper","raw_affiliation_strings":["National Institute of Informatics,Japan","National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354569","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0001-6777-3487"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["MIT-IBM Watson AI Lab,USA","MIT-IBM Watson AI Lab, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT-IBM Watson AI Lab,USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"MIT-IBM Watson AI Lab, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112248869","display_name":"Shiyu Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiyu Chang","raw_affiliation_strings":["MIT-IBM Watson AI Lab,USA","MIT-IBM Watson AI Lab, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT-IBM Watson AI Lab,USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"MIT-IBM Watson AI Lab, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030425371","display_name":"Kaizhi Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaizhi Qian","raw_affiliation_strings":["MIT-IBM Watson AI Lab,USA","MIT-IBM Watson AI Lab, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT-IBM Watson AI Lab,USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"MIT-IBM Watson AI Lab, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058593712","display_name":"Yi-Lun Liao","orcid":"https://orcid.org/0000-0002-5299-6749"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi-Lun Liao","raw_affiliation_strings":["MIT CSAIL,USA","MIT CSAIL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL,USA","institution_ids":[]},{"raw_affiliation_string":"MIT CSAIL, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058729228","display_name":"Yung-Sung Chuang","orcid":"https://orcid.org/0000-0002-1723-5063"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yung-Sung Chuang","raw_affiliation_strings":["MIT CSAIL,USA","MIT CSAIL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL,USA","institution_ids":[]},{"raw_affiliation_string":"MIT CSAIL, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039767083","display_name":"Alexander H. Liu","orcid":"https://orcid.org/0000-0003-1628-0855"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander H. Liu","raw_affiliation_strings":["MIT CSAIL,USA","MIT CSAIL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL,USA","institution_ids":[]},{"raw_affiliation_string":"MIT CSAIL, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics,Japan","National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100763986","display_name":"David Cox","orcid":"https://orcid.org/0000-0002-2189-9743"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Cox","raw_affiliation_strings":["MIT-IBM Watson AI Lab,USA","MIT-IBM Watson AI Lab, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT-IBM Watson AI Lab,USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"MIT-IBM Watson AI Lab, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["MIT CSAIL,USA","MIT CSAIL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL,USA","institution_ids":[]},{"raw_affiliation_string":"MIT CSAIL, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":11,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4152,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.54874105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"8447","last_page":"8451"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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/T12031","display_name":"Speech and dialogue systems","score":0.9972000122070312,"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/naturalness","display_name":"Naturalness","score":0.9552825093269348},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.8276654481887817},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.808855414390564},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7359399199485779},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7243143320083618},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5410235524177551},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5151320695877075},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.47401079535484314},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4695107638835907},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42511850595474243}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9552825093269348},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.8276654481887817},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.808855414390564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7359399199485779},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7243143320083618},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5410235524177551},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5151320695877075},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.47401079535484314},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4695107638835907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42511850595474243},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747728","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747728","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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","score":0.5799999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2112984492","https://openalex.org/W2129142580","https://openalex.org/W2519091744","https://openalex.org/W2802201485","https://openalex.org/W2805003733","https://openalex.org/W2903739847","https://openalex.org/W2915589364","https://openalex.org/W2946200149","https://openalex.org/W2949382160","https://openalex.org/W2963300588","https://openalex.org/W2963813662","https://openalex.org/W2963975282","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2970006822","https://openalex.org/W2970730223","https://openalex.org/W2975044525","https://openalex.org/W2993118648","https://openalex.org/W2995233853","https://openalex.org/W2999160446","https://openalex.org/W3000389243","https://openalex.org/W3015282541","https://openalex.org/W3015338123","https://openalex.org/W3033411150","https://openalex.org/W3035068567","https://openalex.org/W3036601975","https://openalex.org/W3038041907","https://openalex.org/W3038172701","https://openalex.org/W3092028330","https://openalex.org/W3098403858","https://openalex.org/W3099782249","https://openalex.org/W3123097577","https://openalex.org/W3129651364","https://openalex.org/W3130016944","https://openalex.org/W3160919572","https://openalex.org/W3161890269","https://openalex.org/W3162309234","https://openalex.org/W3166714886","https://openalex.org/W3174758275","https://openalex.org/W3178268375","https://openalex.org/W3198769980","https://openalex.org/W3213925038","https://openalex.org/W4287121455","https://openalex.org/W4287828539","https://openalex.org/W4294619240","https://openalex.org/W4298580827","https://openalex.org/W4362724041","https://openalex.org/W6748409065","https://openalex.org/W6751979845","https://openalex.org/W6753855596","https://openalex.org/W6759263581","https://openalex.org/W6763832098","https://openalex.org/W6767111847","https://openalex.org/W6768205276","https://openalex.org/W6771024825","https://openalex.org/W6771763809","https://openalex.org/W6773094808","https://openalex.org/W6774302960","https://openalex.org/W6778823374","https://openalex.org/W6779871621","https://openalex.org/W6780218876","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6787300339","https://openalex.org/W6796551075","https://openalex.org/W6796730497","https://openalex.org/W6798451072","https://openalex.org/W6843673214","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W4392904630","https://openalex.org/W2079655441","https://openalex.org/W169399214","https://openalex.org/W3008088358","https://openalex.org/W4252942110","https://openalex.org/W1604114751","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W4391272374","https://openalex.org/W2081919107"],"abstract_inverted_index":{"Are":[0],"end-to-end":[1,83],"text-to-speech":[2],"(TTS)":[3],"models":[4,11,85,94,137],"over-parametrized?":[5],"To":[6],"what":[7,15],"extent":[8],"can":[9,95],"these":[10],"be":[12],"pruned,":[13],"and":[14,35,44,70,74,104,119,130,134],"happens":[16],"to":[17,28,66,141],"their":[18],"synthesis":[19],"capabilities?":[20],"This":[21],"work":[22,123],"serves":[23],"as":[24],"a":[25],"starting":[26],"point":[27],"explore":[29,53],"pruning":[30],"both":[31],"spectrogram":[32],"prediction":[33],"networks":[34],"vocoders.":[36],"We":[37],"thoroughly":[38],"investigate":[39],"the":[40],"tradeoffs":[41],"between":[42],"sparsity":[43],"its":[45],"subsequent":[46],"effects":[47],"on":[48,115,145],"synthetic":[49,97],"speech.":[50],"Additionally,":[51],"we":[52],"several":[54],"aspects":[55],"of":[56,60,110],"TTS":[57,84,93,148],"pruning:":[58],"amount":[59],"finetuning":[61],"data":[62],"versus":[63],"sparsity,":[64],"TTS-Augmentation":[65],"utilize":[67],"unspoken":[68],"text,":[69],"combining":[71],"knowledge":[72],"distillation":[73],"pruning.":[75],"Our":[76],"findings":[77,120],"suggest":[78],"that":[79],"not":[80],"only":[81],"are":[82,113,124,138],"highly":[86],"prunable,":[87],"but":[88],"also,":[89],"perhaps":[90],"surprisingly,":[91],"pruned":[92,136],"produce":[96],"speech":[98],"with":[99,106],"equal":[100],"or":[101],"higher":[102],"naturalness":[103],"intelligibility,":[105],"similar":[107],"prosody.":[108],"All":[109],"our":[111],"experiments":[112],"conducted":[114],"publicly":[116],"available":[117,140],"models,":[118],"in":[121,147],"this":[122],"backed":[125],"by":[126],"large-scale":[127],"subjective":[128],"tests":[129],"objective":[131],"measures.":[132],"Code":[133],"200":[135],"made":[139],"facilitate":[142],"future":[143],"research":[144],"efficiency":[146],"<sup":[149],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[150],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[151],".":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-13T07:54:00.901334","created_date":"2025-10-10T00:00:00"}