{"id":"https://openalex.org/W2428702538","doi":"https://doi.org/10.21437/interspeech.2016-522","title":"Fast, Compact, and High Quality LSTM-RNN Based Statistical Parametric Speech Synthesizers for Mobile Devices","display_name":"Fast, Compact, and High Quality LSTM-RNN Based Statistical Parametric Speech Synthesizers for Mobile Devices","publication_year":2016,"publication_date":"2016-08-29","ids":{"openalex":"https://openalex.org/W2428702538","doi":"https://doi.org/10.21437/interspeech.2016-522","mag":"2428702538"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-522","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1606.06061","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003420204","display_name":"Heiga Zen","orcid":"https://orcid.org/0000-0002-8959-5471"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Heiga Zen","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024140675","display_name":"Yannis Agiomyrgiannakis","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yannis Agiomyrgiannakis","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059028171","display_name":"Niels Egberts","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niels Egberts","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027496024","display_name":"Fergus Henderson","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fergus Henderson","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075464597","display_name":"Przemys\u0142aw Szczepaniak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Przemys\u0142aw Szczepaniak","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5003420204"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":3.9991,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.94425848,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2273","last_page":"2277"},"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":0.998199999332428,"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/T11309","display_name":"Music and Audio Processing","score":0.9968000054359436,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.8148446083068848},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.808205246925354},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7279458045959473},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6674796342849731},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.5739342570304871},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5430445671081543},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5133835077285767},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.49002039432525635},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.4159672260284424},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3987312912940979},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.30620241165161133},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08105772733688354}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8148446083068848},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.808205246925354},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7279458045959473},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6674796342849731},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5739342570304871},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5430445671081543},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5133835077285767},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.49002039432525635},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.4159672260284424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3987312912940979},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30620241165161133},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08105772733688354},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2016-522","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1606.06061","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1606.06061","pdf_url":"https://arxiv.org/pdf/1606.06061","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"},{"id":"mag:2428702538","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1606.06061","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1606.06061","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1606.06061","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1606.06061","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1606.06061","pdf_url":"https://arxiv.org/pdf/1606.06061","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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2428702538.pdf","grobid_xml":"https://content.openalex.org/works/W2428702538.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W68089216","https://openalex.org/W1492383498","https://openalex.org/W1499332833","https://openalex.org/W1502723613","https://openalex.org/W1520023877","https://openalex.org/W1571950845","https://openalex.org/W1576227399","https://openalex.org/W1783473872","https://openalex.org/W1990505856","https://openalex.org/W2000200144","https://openalex.org/W2010291496","https://openalex.org/W2059610484","https://openalex.org/W2064675550","https://openalex.org/W2102003408","https://openalex.org/W2103279870","https://openalex.org/W2119196219","https://openalex.org/W2134973740","https://openalex.org/W2150355110","https://openalex.org/W2154920538","https://openalex.org/W2166384354","https://openalex.org/W2239904444","https://openalex.org/W2272308216","https://openalex.org/W2293634267","https://openalex.org/W2294246205","https://openalex.org/W2294797155","https://openalex.org/W2337335398","https://openalex.org/W2394662942","https://openalex.org/W2395700867","https://openalex.org/W2402539796","https://openalex.org/W2404881427","https://openalex.org/W2406009315","https://openalex.org/W2406159955","https://openalex.org/W2507771204","https://openalex.org/W3142087749"],"related_works":["https://openalex.org/W2964301388","https://openalex.org/W2805307277","https://openalex.org/W2806733747","https://openalex.org/W2494654097","https://openalex.org/W2920582663","https://openalex.org/W3196364802","https://openalex.org/W1533416326","https://openalex.org/W2803235095","https://openalex.org/W3113409450","https://openalex.org/W2763238567","https://openalex.org/W2399853303","https://openalex.org/W3033124456","https://openalex.org/W2794838827","https://openalex.org/W2963302875","https://openalex.org/W2890012642","https://openalex.org/W2404856031","https://openalex.org/W2005708641","https://openalex.org/W2292359288","https://openalex.org/W2886180730","https://openalex.org/W2891628540"],"abstract_inverted_index":{"Acoustic":[0],"models":[1,33],"based":[2,29,88],"on":[3,30,45],"long":[4],"short-term":[5],"memory":[6],"recurrent":[7],"neural":[8],"networks":[9],"(LSTM-RNNs)":[10],"were":[11],"applied":[12],"to":[13,76],"statistical":[14],"parametric":[15],"speech":[16,94],"synthesis":[17,95],"(SPSS)":[18],"and":[19,25,52,90],"showed":[20],"significant":[21],"improvements":[22],"in":[23,63,79],"naturalness":[24],"latency":[26],"over":[27],"those":[28],"hidden":[31],"Markov":[32],"(HMMs).":[34],"This":[35],"paper":[36],"describes":[37],"further":[38],"optimizations":[39,70],"of":[40],"LSTM-RNN-based":[41,73],"SPSS":[42,74,78,89],"for":[43],"deployment":[44],"mobile":[46],"devices;":[47],"weight":[48],"quantization,":[49],"multi-frame":[50],"inference,":[51],"robust":[53],"inference":[54],"using":[55],"an":[56],"\u03b5-contaminated":[57],"Gaussian":[58],"loss":[59],"function.":[60],"Experimental":[61],"results":[62],"subjective":[64],"listening":[65],"tests":[66],"show":[67],"that":[68],"these":[69],"can":[71],"make":[72],"comparable":[75],"HMM-based":[77],"runtime":[80],"speed":[81],"while":[82],"maintaining":[83],"naturalness.":[84],"Evaluations":[85],"between":[86],"LSTM-RNN-":[87],"HMM-driven":[91],"unit":[92],"selection":[93],"are":[96],"also":[97],"presented.":[98]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":5}],"updated_date":"2026-03-23T06:02:50.125483","created_date":"2025-10-10T00:00:00"}