{"id":"https://openalex.org/W2982174878","doi":"https://doi.org/10.1109/icassp40776.2020.9054106","title":"Location-Relative Attention Mechanisms for Robust Long-Form Speech Synthesis","display_name":"Location-Relative Attention Mechanisms for Robust Long-Form Speech Synthesis","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2982174878","doi":"https://doi.org/10.1109/icassp40776.2020.9054106","mag":"2982174878"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/1910.10288","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056579280","display_name":"Eric Battenberg","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":true,"raw_author_name":"Eric Battenberg","raw_affiliation_strings":["Google Research","Google Research,"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Research,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066591543","display_name":"RJ Skerry-Ryan","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":"R.J. Skerry-Ryan","raw_affiliation_strings":["Google Research","Google Research,"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Research,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022916498","display_name":"Soroosh Mariooryad","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":"Soroosh Mariooryad","raw_affiliation_strings":["Google Research","Google Research,"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Research,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024684905","display_name":"Daisy Stanton","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":"Daisy Stanton","raw_affiliation_strings":["Google Research","Google Research,"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Research,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014395205","display_name":"David Kao","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":"David Kao","raw_affiliation_strings":["Google Research","Google Research,"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Research,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080404214","display_name":"Matt Shannon","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":"Matt Shannon","raw_affiliation_strings":["Google Research","Google Research,"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Research,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024261917","display_name":"Tom Bagby","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":"Tom Bagby","raw_affiliation_strings":["Google Research","Google Research,"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Research,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5056579280"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.6456,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.86895661,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6194","last_page":"6198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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":0.9995999932289124,"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":0.9536307454109192},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.764037013053894},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5766539573669434},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5485312938690186},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4778937101364136},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.44220834970474243},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4327770471572876},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.41167619824409485},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40295571088790894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3921249508857727},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11293202638626099}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9536307454109192},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.764037013053894},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5766539573669434},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5485312938690186},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4778937101364136},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.44220834970474243},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4327770471572876},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.41167619824409485},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40295571088790894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3921249508857727},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11293202638626099},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054106","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054106","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.10288","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.10288","pdf_url":"https://arxiv.org/pdf/1910.10288","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:2982174878","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.10288","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.1910.10288","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.10288","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"},{"id":"doi:10.17023/ngf2-px66","is_oa":true,"landing_page_url":"https://doi.org/10.17023/ngf2-px66","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"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:1910.10288","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.10288","pdf_url":"https://arxiv.org/pdf/1910.10288","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":[{"id":"https://metadata.un.org/sdg/4","score":0.4300000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2982174878.pdf","grobid_xml":"https://content.openalex.org/works/W2982174878.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1810943226","https://openalex.org/W2107860279","https://openalex.org/W2605141709","https://openalex.org/W2795109282","https://openalex.org/W2886769154","https://openalex.org/W2948238043","https://openalex.org/W2963609956","https://openalex.org/W2963827314","https://openalex.org/W2963927338","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2964308564","https://openalex.org/W2971905065","https://openalex.org/W2972702018","https://openalex.org/W6623517193","https://openalex.org/W6638273328","https://openalex.org/W6679434410","https://openalex.org/W6735706088","https://openalex.org/W6736996214","https://openalex.org/W6748409065","https://openalex.org/W6763316926","https://openalex.org/W6768158615","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2964243274","https://openalex.org/W2963609956","https://openalex.org/W3199188494","https://openalex.org/W854541894","https://openalex.org/W2766191375","https://openalex.org/W2963300588","https://openalex.org/W1810943226","https://openalex.org/W3016072087","https://openalex.org/W2970079483","https://openalex.org/W3007580377","https://openalex.org/W2947723875","https://openalex.org/W3196001064","https://openalex.org/W2952470929","https://openalex.org/W3186301694","https://openalex.org/W2949788262","https://openalex.org/W2929514213","https://openalex.org/W3015938946","https://openalex.org/W2767601419","https://openalex.org/W3027588817","https://openalex.org/W2965116050"],"abstract_inverted_index":{"Despite":[0],"the":[1,86,97],"ability":[2,111],"to":[3,65,71,85,112,114,126],"produce":[4],"human-level":[5],"speech":[6],"for":[7,24,133],"in-domain":[8,135],"text,":[9],"attention-based":[10],"end-to-end":[11],"text-to-speech":[12],"(TTS)":[13],"systems":[14],"suffer":[15],"from":[16],"text":[17],"alignment":[18,103],"failures":[19,31],"that":[20,29,40,68,119],"increase":[21],"in":[22,100],"frequency":[23],"out-of-domain":[25],"text.":[26],"We":[27,47,61,95],"show":[28],"these":[30],"can":[32,124],"be":[33],"addressed":[34],"using":[35],"simple":[36,63],"location-relative":[37,54,82],"attention":[38,52,67,83,121],"mechanisms":[39,56,99],"do":[41],"away":[42],"with":[43],"content-based":[44],"query/key":[45],"comparisons.":[46],"compare":[48,96],"two":[49],"families":[50],"of":[51,102],"mechanisms:":[53],"GMM-based":[55,66],"and":[57,74,78,105,110,117,122],"additive":[58,87],"energy-based":[59,88],"mechanisms.":[60],"suggest":[62],"modifications":[64],"allow":[69],"it":[70],"align":[72],"quickly":[73],"consistently":[75],"during":[76,107],"training,":[77,108],"introduce":[79],"a":[80],"new":[81],"mechanism":[84],"family,":[89],"called":[90],"Dynamic":[91],"Convolution":[92],"Attention":[93],"(DCA).":[94],"various":[98],"terms":[101],"speed":[104],"consistency":[106],"naturalness,":[109],"generalize":[113,125],"long":[115,128],"utterances,":[116,129],"conclude":[118],"GMM":[120],"DCA":[123],"very":[127],"while":[130],"preserving":[131],"naturalness":[132],"shorter,":[134],"utterances.":[136]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}