{"id":"https://openalex.org/W4408258266","doi":"https://doi.org/10.1109/tencon61640.2024.10902970","title":"SNIPER Training: Single-Shot Sparse Training for Text-to-Speech","display_name":"SNIPER Training: Single-Shot Sparse Training for Text-to-Speech","publication_year":2024,"publication_date":"2024-12-01","ids":{"openalex":"https://openalex.org/W4408258266","doi":"https://doi.org/10.1109/tencon61640.2024.10902970"},"language":"en","primary_location":{"id":"doi:10.1109/tencon61640.2024.10902970","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon61640.2024.10902970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2024 - 2024 IEEE Region 10 Conference (TENCON)","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/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":["Audio, Music, and AI Lab, Singapore University of Technology and Design,Singapore"],"affiliations":[{"raw_affiliation_string":"Audio, Music, and AI Lab, Singapore University of Technology and Design,Singapore","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"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Huayun Zhang","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"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/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"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 F. Chen","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001303929","display_name":"Berrak \u015ei\u015fman","orcid":"https://orcid.org/0000-0001-8078-3305"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Berrak Sisman","raw_affiliation_strings":["Speech &#x0026; Machine Learning Lab, The University of Texas,Dallas,USA"],"affiliations":[{"raw_affiliation_string":"Speech &#x0026; Machine Learning Lab, The University of Texas,Dallas,USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069548004","display_name":"Dorien Herremans","orcid":"https://orcid.org/0000-0001-8607-1640"},"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":"Dorien Herremans","raw_affiliation_strings":["Audio, Music, and AI Lab, Singapore University of Technology and Design,Singapore"],"affiliations":[{"raw_affiliation_string":"Audio, Music, and AI Lab, Singapore University of Technology and Design,Singapore","institution_ids":["https://openalex.org/I152815399"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5002258189"],"corresponding_institution_ids":["https://openalex.org/I152815399"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25915878,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"327","last_page":"330"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9954000115394592,"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":0.995199978351593,"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/training","display_name":"Training (meteorology)","score":0.8421005010604858},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7775533199310303},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.7098255157470703},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5849905014038086},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5220268368721008},{"id":"https://openalex.org/keywords/single-shot","display_name":"Single shot","score":0.5013976097106934},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.47060734033584595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4463045299053192},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35446450114250183},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07943299412727356}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.8421005010604858},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7775533199310303},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7098255157470703},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5849905014038086},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5220268368721008},{"id":"https://openalex.org/C3019835501","wikidata":"https://www.wikidata.org/wiki/Q1310130","display_name":"Single shot","level":2,"score":0.5013976097106934},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.47060734033584595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4463045299053192},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35446450114250183},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07943299412727356},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tencon61640.2024.10902970","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon61640.2024.10902970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2024 - 2024 IEEE Region 10 Conference (TENCON)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2023701920","https://openalex.org/W2380489056","https://openalex.org/W2894740066","https://openalex.org/W2956434358","https://openalex.org/W2963319203","https://openalex.org/W3004127905","https://openalex.org/W3005842225","https://openalex.org/W3015338123","https://openalex.org/W3033411150","https://openalex.org/W3041148953","https://openalex.org/W3104688113","https://openalex.org/W3121696187","https://openalex.org/W3127067080","https://openalex.org/W3166316513","https://openalex.org/W3203852729","https://openalex.org/W3206375275","https://openalex.org/W3213847610","https://openalex.org/W4287208846","https://openalex.org/W4287327026","https://openalex.org/W4287391717","https://openalex.org/W4288089799","https://openalex.org/W4296070221","https://openalex.org/W4372346788","https://openalex.org/W4385823417","https://openalex.org/W6751979845","https://openalex.org/W6755166560","https://openalex.org/W6769627184","https://openalex.org/W6772027524","https://openalex.org/W6778823374","https://openalex.org/W6779253501","https://openalex.org/W6779460946","https://openalex.org/W6788034315","https://openalex.org/W6788811087","https://openalex.org/W6789946416","https://openalex.org/W6790943123","https://openalex.org/W6795651637","https://openalex.org/W6795861741","https://openalex.org/W6802659129","https://openalex.org/W7038139519"],"related_works":["https://openalex.org/W3142396426","https://openalex.org/W2471333042","https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W4396643691","https://openalex.org/W4404739899","https://openalex.org/W146529714","https://openalex.org/W4402383816","https://openalex.org/W2316500695","https://openalex.org/W1999226266"],"abstract_inverted_index":{"Text-to-speech":[0],"(TTS)":[1],"models":[2,24,29,40,50,133,136],"have":[3,17],"achieved":[4],"remarkable":[5],"naturalness":[6],"in":[7,120,145],"recent":[8],"years,":[9],"yet":[10],"like":[11],"most":[12],"deep":[13],"neural":[14],"models,":[15,141],"they":[16],"more":[18,91],"parameters":[19],"than":[20,38,93],"necessary.":[21],"Sparse":[22],"TTS":[23,49],"can":[25],"improve":[26],"on":[27,109,152],"dense":[28,39,94,140],"via":[30],"pruning":[31],"and":[32,128,137],"extra":[33],"retraining,":[34],"or":[35],"converge":[36],"faster":[37],"with":[41,126,142],"some":[42],"performance":[43],"loss.":[44],"Thus,":[45],"we":[46,113],"propose":[47],"training":[48,61,124,146],"using":[51],"decaying":[52],"sparsity,":[53],"i.e.":[54],"a":[55,65,85],"high":[56],"initial":[57],"sparsity":[58,83],"to":[59,69,84,116],"accelerate":[60],"first,":[62],"followed":[63],"by":[64],"progressive":[66],"rate":[67],"reduction":[68],"obtain":[70,117],"better":[71,118],"eventual":[72],"performance.":[73],"This":[74],"decremental":[75],"approach":[76],"differs":[77],"from":[78],"current":[79],"methods":[80],"of":[81],"incrementing":[82],"desired":[86],"target,":[87],"which":[88],"costs":[89],"significantly":[90],"time":[92],"training.":[95,106],"We":[96],"call":[97],"our":[98],"method":[99],"SNIPER":[100],"training:":[101],"Single-shot":[102],"Initialization":[103],"Pruning":[104],"Evolving-Rate":[105],"Our":[107,148],"experiments":[108],"FastSpeech2":[110],"show":[111],"that":[112,129],"were":[114],"able":[115],"losses":[119],"the":[121,130],"first":[122],"few":[123],"epochs":[125],"SNIPER,":[127],"final":[131],"SNIPER-trained":[132],"outperformed":[134],"constant-sparsity":[135],"edged":[138],"out":[139],"negligible":[143],"difference":[144],"time.":[147],"code":[149],"is":[150],"available":[151],"Github<sup":[153],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[154,157],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[155],"<sup":[156],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>https://github.com/iamanigeeit/sniper.":[158]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}