{"id":"https://openalex.org/W2889260122","doi":"https://doi.org/10.21437/iberspeech.2018-32","title":"Self-Attention Linguistic-Acoustic Decoder","display_name":"Self-Attention Linguistic-Acoustic Decoder","publication_year":2018,"publication_date":"2018-11-19","ids":{"openalex":"https://openalex.org/W2889260122","doi":"https://doi.org/10.21437/iberspeech.2018-32","mag":"2889260122"},"language":"en","primary_location":{"id":"doi:10.21437/iberspeech.2018-32","is_oa":false,"landing_page_url":"https://doi.org/10.21437/iberspeech.2018-32","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IberSPEECH 2018","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1808.10678","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101557983","display_name":"Santiago Pascual","orcid":"https://orcid.org/0000-0002-8365-7387"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Santiago Pascual","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000405202","display_name":"Antonio Bonafonte","orcid":"https://orcid.org/0000-0002-6240-9915"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antonio Bonafonte","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103092198","display_name":"Joan Serr\u00e0","orcid":"https://orcid.org/0000-0003-1303-6558"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joan Serr\u00e0","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"152","last_page":"156"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9972000122070312,"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":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.7655320763587952},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6890352964401245},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6005253791809082},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5527971982955933},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.530914843082428},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4192812740802765},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.4185005724430084},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4065006971359253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30976176261901855},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.16525590419769287},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13093724846839905}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7655320763587952},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6890352964401245},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6005253791809082},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5527971982955933},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.530914843082428},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4192812740802765},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.4185005724430084},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4065006971359253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30976176261901855},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.16525590419769287},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13093724846839905},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/iberspeech.2018-32","is_oa":false,"landing_page_url":"https://doi.org/10.21437/iberspeech.2018-32","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IberSPEECH 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1808.10678","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.10678","pdf_url":"https://arxiv.org/pdf/1808.10678","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":"","raw_type":"text"},{"id":"mag:2889260122","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1808.10678.pdf","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.1808.10678","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1808.10678","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1808.10678","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.10678","pdf_url":"https://arxiv.org/pdf/1808.10678","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2889260122.pdf","grobid_xml":"https://content.openalex.org/works/W2889260122.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1571950845","https://openalex.org/W1576227399","https://openalex.org/W1924770834","https://openalex.org/W2045158511","https://openalex.org/W2085261163","https://openalex.org/W2095705004","https://openalex.org/W2102003408","https://openalex.org/W2106564373","https://openalex.org/W2134973740","https://openalex.org/W2276892362","https://openalex.org/W2295406225","https://openalex.org/W2399057275","https://openalex.org/W2404881427","https://openalex.org/W2548585807","https://openalex.org/W2562274522","https://openalex.org/W2594927458","https://openalex.org/W2626778328","https://openalex.org/W2798405286","https://openalex.org/W2949888546","https://openalex.org/W2964060510","https://openalex.org/W2964308564","https://openalex.org/W3196867271"],"related_works":["https://openalex.org/W2963601301","https://openalex.org/W2981696585","https://openalex.org/W3132015784","https://openalex.org/W2937909162","https://openalex.org/W3014973941","https://openalex.org/W3210679021","https://openalex.org/W3129640789","https://openalex.org/W3013896298","https://openalex.org/W3199015956","https://openalex.org/W3096082720","https://openalex.org/W3132002396","https://openalex.org/W3095913803","https://openalex.org/W2913554070","https://openalex.org/W2785765285","https://openalex.org/W2994785103","https://openalex.org/W3031135612","https://openalex.org/W2969521066","https://openalex.org/W2985287635","https://openalex.org/W2594927458","https://openalex.org/W2799930831"],"abstract_inverted_index":{"The":[0],"conversion":[1],"from":[2,11],"text":[3],"to":[4,13,49,53,56,64,109],"speech":[5,154],"relies":[6],"on":[7,76,144,157],"the":[8,30,42,66,77,97,151],"accurate":[9],"mapping":[10],"linguistic":[12],"acoustic":[14],"symbol":[15],"sequences,":[16],"for":[17,150],"which":[18],"current":[19],"practice":[20],"employs":[21],"recurrent":[22,26,83,111],"statistical":[23],"models":[24,35],"like":[25,162],"neural":[27],"networks.":[28],"Despite":[29],"good":[31],"performance":[32],"of":[33,38,68,105,119,141,153],"such":[34],"(in":[36],"terms":[37,104,118],"low":[39],"distortion":[40,106,129],"in":[41,103,117],"generated":[43],"speech),":[44],"their":[45],"recursive":[46,69],"structure":[47,70],"tends":[48],"make":[50],"them":[51,87],"slow":[52],"train":[54],"and":[55,90,132],"sample":[57],"from.":[58],"In":[59],"this":[60],"work,":[61],"we":[62],"try":[63],"overcome":[65],"limitations":[67],"by":[71],"using":[72],"a":[73,110],"module":[74],"based":[75],"transformer":[78],"decoder":[79,99],"network,":[80],"designed":[81],"without":[82],"connections":[84],"but":[85,135],"emulating":[86],"with":[88,159],"attention":[89],"positioning":[91],"codes.":[92],"Our":[93],"results":[94],"show":[95],"that":[96],"proposed":[98],"network":[100],"is":[101,137,148],"competitive":[102],"when":[107],"compared":[108],"baseline,":[112],"whilst":[113],"being":[114],"significantly":[115],"faster":[116,143],"CPU":[120],"inference":[121,147],"time.":[122],"On":[123],"average,":[124],"it":[125,136],"increases":[126],"Mel":[127],"cepstral":[128],"between":[130],"0.1":[131],"0.3":[133],"dB,":[134],"over":[138],"an":[139],"order":[140],"magnitude":[142],"average.":[145],"Fast":[146],"important":[149],"deployment":[152],"synthesis":[155],"systems":[156],"devices":[158],"restricted":[160],"resources,":[161],"mobile":[163],"phones":[164],"or":[165],"embedded":[166],"systems,":[167],"where":[168],"speaking":[169],"virtual":[170],"assistants":[171],"are":[172],"gaining":[173],"importance.":[174]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}