{"id":"https://openalex.org/W4296070221","doi":"https://doi.org/10.21437/interspeech.2022-10626","title":"EPIC TTS Models: Empirical Pruning Investigations Characterizing Text-To-Speech Models","display_name":"EPIC TTS Models: Empirical Pruning Investigations Characterizing Text-To-Speech Models","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296070221","doi":"https://doi.org/10.21437/interspeech.2022-10626"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10626","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10626","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.10890","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002258189","display_name":"Perry Lam","orcid":"https://orcid.org/0000-0001-9607-0756"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Perry Lam","raw_affiliation_strings":["Singapore University of Technology and Design"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102856166","display_name":"Huayun Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Huayun Zhang","raw_affiliation_strings":["Institute for Infocomm Research, A"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014190404","display_name":"Nancy F. Chen","orcid":"https://orcid.org/0000-0003-0872-5877"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Nancy Chen","raw_affiliation_strings":["Institute for Infocomm Research, A"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001303929","display_name":"Berrak \u015ei\u015fman","orcid":"https://orcid.org/0000-0001-8078-3305"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Berrak Sisman","raw_affiliation_strings":["Singapore University of Technology and Design"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5002258189"],"corresponding_institution_ids":["https://openalex.org/I152815399"],"apc_list":null,"apc_paid":null,"fwci":0.1047,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.2958605,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"823","last_page":"827"},"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/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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":0.9980999827384949,"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":0.8141754865646362},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6488860249519348},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6406408548355103},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.59465491771698},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.5649659037590027},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5364457368850708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5027198791503906},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4925864338874817},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.48817259073257446},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4602344036102295},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41397079825401306},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0912063717842102}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8141754865646362},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6488860249519348},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6406408548355103},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.59465491771698},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5649659037590027},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5364457368850708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5027198791503906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4925864338874817},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.48817259073257446},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4602344036102295},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41397079825401306},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0912063717842102},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"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":2,"locations":[{"id":"doi:10.21437/interspeech.2022-10626","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10626","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2209.10890","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.10890","pdf_url":"https://arxiv.org/pdf/2209.10890","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2209.10890","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.10890","pdf_url":"https://arxiv.org/pdf/2209.10890","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W38194800","https://openalex.org/W2023701920","https://openalex.org/W2025713906","https://openalex.org/W2156150815","https://openalex.org/W2294543795","https://openalex.org/W2588048611","https://openalex.org/W2604184139","https://openalex.org/W2786868129","https://openalex.org/W2805003733","https://openalex.org/W2891710009","https://openalex.org/W2894740066","https://openalex.org/W2915589364","https://openalex.org/W2951200949","https://openalex.org/W2956434358","https://openalex.org/W2963363373","https://openalex.org/W2964243274","https://openalex.org/W2990844796","https://openalex.org/W2996428491","https://openalex.org/W3005842225","https://openalex.org/W3015338123","https://openalex.org/W3015922793","https://openalex.org/W3021119228","https://openalex.org/W3035811951","https://openalex.org/W3046330735","https://openalex.org/W3097376233","https://openalex.org/W3104263050","https://openalex.org/W3196467321","https://openalex.org/W3203852729","https://openalex.org/W4221167110","https://openalex.org/W4287629681","https://openalex.org/W4287828539"],"related_works":["https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W169399214","https://openalex.org/W4252942110","https://openalex.org/W1604114751","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W4391272374","https://openalex.org/W2081919107","https://openalex.org/W1984347656"],"abstract_inverted_index":{"Neural":[0],"models":[1,16],"are":[2,51],"known":[3],"to":[4,46,97,112],"be":[5,118],"over-parameterized,":[6],"and":[7,61,69,87,93,116],"recent":[8],"work":[9,141],"has":[10,27],"shown":[11],"that":[12,102,142],"sparse":[13,25,56],"text-to-speech":[14,147],"(TTS)":[15],"can":[17,108,117],"outperform":[18],"dense":[19],"models.":[20],"Although":[21],"a":[22,66],"plethora":[23],"of":[24,54,72,84],"methods":[26,34],"been":[28,37],"proposed":[29],"for":[30],"other":[31],"domains,":[32],"such":[33],"have":[35],"rarely":[36],"applied":[38],"in":[39,146],"TTS.":[40],"In":[41],"this":[42,137],"work,":[43],"we":[44,100],"seek":[45],"answer":[47],"the":[48,52,59,70,79,82,139],"question:":[49],"what":[50],"characteristics":[53],"selected":[55],"techniques":[57],"on":[58],"performance":[60,80,111,127],"model":[62,91],"complexity?":[63],"We":[64,76],"compare":[65],"Tacotron2":[67],"baseline":[68],"results":[71],"applying":[73],"five":[74],"techniques.":[75],"then":[77],"evaluate":[78],"via":[81],"factors":[83],"naturalness,":[85],"intelligibility":[86],"prosody,":[88],"while":[89,122],"reporting":[90],"size":[92],"training":[94,107,115],"time.":[95],"Complementary":[96],"prior":[98],"research,":[99],"find":[101],"pruning":[103,113],"before":[104],"or":[105],"during":[106],"achieve":[109],"similar":[110],"after":[114],"trained":[119],"much":[120,128],"faster,":[121],"removing":[123,131],"entire":[124],"neurons":[125],"degrades":[126],"more":[129],"than":[130],"parameters.":[132],"To":[133],"our":[134],"best":[135],"knowledge,":[136],"is":[138],"first":[140],"compares":[143],"sparsity":[144],"paradigms":[145],"synthesis.":[148]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}