{"id":"https://openalex.org/W4210684870","doi":"https://doi.org/10.1109/asru51503.2021.9688154","title":"On-Device Neural Speech Synthesis","display_name":"On-Device Neural Speech Synthesis","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210684870","doi":"https://doi.org/10.1109/asru51503.2021.9688154"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688154","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5086878243","display_name":"Sivanand Achanta","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sivanand Achanta","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026835553","display_name":"Albert Antony","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Albert Antony","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010570444","display_name":"Ladan Golipour","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ladan Golipour","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005526135","display_name":"Jiangchuan Li","orcid":"https://orcid.org/0000-0002-6489-4766"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiangchuan Li","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000571465","display_name":"Tuomo Raitio","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tuomo Raitio","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015798689","display_name":"Ramya Rasipuram","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ramya Rasipuram","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079250162","display_name":"Francesco Rossi","orcid":"https://orcid.org/0000-0002-5851-0412"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Francesco Rossi","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044514303","display_name":"Jennifer Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jennifer Shi","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014072981","display_name":"Jaimin Upadhyay","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jaimin Upadhyay","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064317196","display_name":"David Winarsky","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Winarsky","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061758260","display_name":"Hepeng Zhang","orcid":"https://orcid.org/0000-0001-7806-407X"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hepeng Zhang","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210107260"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1155","last_page":"1161"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9976999759674072,"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":0.9965000152587891,"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":0.8229385614395142},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8034693002700806},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7334244251251221},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.670729398727417},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5683407187461853},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5635937452316284},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5079856514930725},{"id":"https://openalex.org/keywords/psqm","display_name":"PSQM","score":0.49618345499038696},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4577350616455078},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.44921213388442993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3126189708709717},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10676383972167969}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8229385614395142},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8034693002700806},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7334244251251221},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.670729398727417},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5683407187461853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5635937452316284},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5079856514930725},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.49618345499038696},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4577350616455078},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.44921213388442993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3126189708709717},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10676383972167969},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688154","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2519091744","https://openalex.org/W2547875792","https://openalex.org/W2548228487","https://openalex.org/W2584032004","https://openalex.org/W2591927543","https://openalex.org/W2619368999","https://openalex.org/W2747681982","https://openalex.org/W2766812927","https://openalex.org/W2769810959","https://openalex.org/W2901997113","https://openalex.org/W2946200149","https://openalex.org/W2954386831","https://openalex.org/W2963091184","https://openalex.org/W2963300588","https://openalex.org/W2963609956","https://openalex.org/W2963975282","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2972702018","https://openalex.org/W3033411150","https://openalex.org/W3161296985","https://openalex.org/W3161782335","https://openalex.org/W4287761884","https://openalex.org/W4294619240","https://openalex.org/W4298580827","https://openalex.org/W6732429163","https://openalex.org/W6745697700","https://openalex.org/W6748409065","https://openalex.org/W6753855596","https://openalex.org/W6756197946","https://openalex.org/W6763832098","https://openalex.org/W6765987481","https://openalex.org/W6767111847","https://openalex.org/W6778823374","https://openalex.org/W6779337556","https://openalex.org/W6786041167"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W642007152","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W2401827384","https://openalex.org/W4304187160","https://openalex.org/W596245619","https://openalex.org/W2536333783","https://openalex.org/W2168417340","https://openalex.org/W2131711534"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,81],"text-to-speech":[3],"(TTS)":[4],"synthesis,":[5],"such":[6],"as":[7,36,46],"Tacotron":[8],"and":[9,50,73,86,96,131],"WaveRNN,":[10],"have":[11,77],"made":[12],"it":[13,37],"possible":[14],"to":[15,62],"construct":[16],"a":[17,31],"fully":[18],"neural":[19],"network":[20],"based":[21],"TTS":[22],"system,":[23],"by":[24],"coupling":[25],"the":[26,66,71],"two":[27],"components":[28],"together.":[29],"Such":[30],"system":[32,56,72,116],"is":[33],"conceptually":[34],"sim-ple":[35],"only":[38,105],"takes":[39],"grapheme":[40],"or":[41,60],"phoneme":[42],"input,":[43],"uses":[44],"Mel-spectrogram":[45],"an":[47],"intermediate":[48],"feature,":[49],"directly":[51],"generates":[52],"speech":[53,83,122],"samples.":[54],"The":[55,114],"achieves":[57],"quality":[58],"equal":[59],"close":[61],"natural":[63],"speech.":[64],"However,":[65],"high":[67],"computational":[68],"cost":[69],"of":[70],"issues":[74],"with":[75],"robustness":[76],"limited":[78],"their":[79],"usage":[80],"real-world":[82],"synthesis":[84],"applications":[85],"products.":[87],"In":[88],"this":[89],"paper,":[90],"we":[91],"present":[92],"key":[93],"modeling":[94],"improvements":[95],"optimization":[97],"strategies":[98],"that":[99],"enable":[100],"deploying":[101],"these":[102],"models,":[103],"not":[104],"on":[106,111,129,137],"GPU":[107],"servers,":[108],"but":[109],"also":[110],"mobile":[112,138],"devices.":[113,139],"proposed":[115],"can":[117],"generate":[118],"high-quality":[119],"24":[120],"kHz":[121],"at":[123],"5x":[124],"faster":[125,133],"than":[126,134],"real":[127,135],"time":[128,136],"server":[130],"3x":[132]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}