{"id":"https://openalex.org/W1499332833","doi":"https://doi.org/10.1109/icassp.2015.7178814","title":"Deep neural networks employing Multi-Task Learning and stacked bottleneck features for speech synthesis","display_name":"Deep neural networks employing Multi-Task Learning and stacked bottleneck features for speech synthesis","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1499332833","doi":"https://doi.org/10.1109/icassp.2015.7178814","mag":"1499332833"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/files/24726040/icassp2015_dnn_tts.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102765381","display_name":"Zhizheng Wu","orcid":"https://orcid.org/0009-0001-1192-9857"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhizheng Wu","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, United Kingdom","[Centre for Speech Technology Research, University of Edinburgh, United Kingdom]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"[Centre for Speech Technology Research, University of Edinburgh, United Kingdom]","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019012876","display_name":"Cassia Valentini-Botinhao","orcid":"https://orcid.org/0000-0002-3486-8620"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cassia Valentini-Botinhao","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, United Kingdom","[Centre for Speech Technology Research, University of Edinburgh, United Kingdom]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"[Centre for Speech Technology Research, University of Edinburgh, United Kingdom]","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110238677","display_name":"Oliver Watts","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oliver Watts","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, United Kingdom","[Centre for Speech Technology Research, University of Edinburgh, United Kingdom]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"[Centre for Speech Technology Research, University of Edinburgh, United Kingdom]","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, United Kingdom","[Centre for Speech Technology Research, University of Edinburgh, United Kingdom]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"[Centre for Speech Technology Research, University of Edinburgh, United Kingdom]","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":247,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4460","last_page":"4464"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9973000288009644,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9965999722480774,"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":0.7825440168380737},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7034143805503845},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6530110836029053},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.612324595451355},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.581859827041626},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5718348026275635},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5538705587387085},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5159293413162231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5150012969970703},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5009989738464355},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.48531216382980347},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43418294191360474},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33963531255722046},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33206629753112793},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07275015115737915}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7825440168380737},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7034143805503845},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6530110836029053},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.612324595451355},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.581859827041626},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5718348026275635},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5538705587387085},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5159293413162231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5150012969970703},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5009989738464355},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.48531216382980347},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43418294191360474},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33963531255722046},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33206629753112793},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07275015115737915},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2015.7178814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/da1e4436-e4ec-4bd3-8671-065865d2b92a","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/da1e4436-e4ec-4bd3-8671-065865d2b92a","pdf_url":"https://www.research.ed.ac.uk/files/24726040/icassp2015_dnn_tts.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wu, Z, Valentini-Botinhao, C, Watts, O & King, S 2015, Deep neural networks employing multi-task learning and stacked bottleneck features for speech synthesis. in Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on. Brisbane, Australia, pp. 4460-4464. < http://ieeexplore.ieee.org/xpls/icp.jsp?arnumber=7178814 >","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.715.1791","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.715.1791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2015/dnnbmtl_ICASSP15.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:ec_fundedresources/da1e4436-e4ec-4bd3-8671-065865d2b92a","is_oa":false,"landing_page_url":"http://ieeexplore.ieee.org/xpls/icp.jsp?arnumber=7178814","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/da1e4436-e4ec-4bd3-8671-065865d2b92a","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/da1e4436-e4ec-4bd3-8671-065865d2b92a","pdf_url":"https://www.research.ed.ac.uk/files/24726040/icassp2015_dnn_tts.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wu, Z, Valentini-Botinhao, C, Watts, O & King, S 2015, Deep neural networks employing multi-task learning and stacked bottleneck features for speech synthesis. in Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on. Brisbane, Australia, pp. 4460-4464. < http://ieeexplore.ieee.org/xpls/icp.jsp?arnumber=7178814 >","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5899999737739563}],"awards":[{"id":"https://openalex.org/G3790594077","display_name":"Natural Speech Technology","funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4055593462","display_name":null,"funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1499332833.pdf","grobid_xml":"https://content.openalex.org/works/W1499332833.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1514737389","https://openalex.org/W1571950845","https://openalex.org/W1970088388","https://openalex.org/W1979449467","https://openalex.org/W1990505856","https://openalex.org/W2000513720","https://openalex.org/W2020024436","https://openalex.org/W2045158511","https://openalex.org/W2049686551","https://openalex.org/W2078597717","https://openalex.org/W2094035326","https://openalex.org/W2102003408","https://openalex.org/W2105099419","https://openalex.org/W2111194146","https://openalex.org/W2117130368","https://openalex.org/W2123237149","https://openalex.org/W2129142580","https://openalex.org/W2134973740","https://openalex.org/W2150658333","https://openalex.org/W2152175008","https://openalex.org/W2154920538","https://openalex.org/W2160815625","https://openalex.org/W2294797155","https://openalex.org/W2914746235","https://openalex.org/W3140795192","https://openalex.org/W4239943352","https://openalex.org/W4247750718","https://openalex.org/W6634201745","https://openalex.org/W6642711939","https://openalex.org/W6662197066","https://openalex.org/W6675380101","https://openalex.org/W6676358011","https://openalex.org/W6696843773"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W2038801705","https://openalex.org/W2688184458","https://openalex.org/W2904846757"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"use":[4,78],"a":[5,71,120,125,129],"cascade":[6],"of":[7,14,79,87,103],"hidden":[8,67,88],"representations":[9],"to":[10,19,25,34,96],"enable":[11],"the":[12,27,66,77,101,104],"learning":[13],"complex":[15,28],"mappings":[16],"from":[17,30],"input":[18],"output":[20],"features.":[21],"They":[22],"are":[23],"able":[24],"learn":[26],"mapping":[29],"text-based":[31],"linguistic":[32],"features":[33,116],"speech":[35,53],"acoustic":[36],"features,":[37],"and":[38,82,107,128],"so":[39],"perform":[40],"text-to-speech":[41],"synthesis.":[42],"Recent":[43],"results":[44,99],"suggest":[45],"that":[46,65,83,113],"DNNs":[47],"can":[48,73],"produce":[49],"more":[50],"natural":[51],"synthetic":[52],"than":[54],"conventional":[55],"HMM-based":[56],"statistical":[57],"parametric":[58],"systems.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63,111],"show":[64],"representation":[68],"used":[69],"within":[70],"DNN":[72,127],"be":[74],"improved":[75],"through":[76],"Multi-Task":[80],"Learning,":[81],"stacking":[84],"multiple":[85],"frames":[86],"layer":[89],"activations":[90],"(stacked":[91],"bottleneck":[92,115],"features)":[93],"also":[94],"leads":[95],"improvements.":[97],"Experimental":[98],"confirmed":[100],"effectiveness":[102],"proposed":[105],"methods,":[106],"in":[108,117],"listening":[109],"tests":[110],"find":[112],"stacked":[114],"particular":[118],"offer":[119],"significant":[121],"improvement":[122],"over":[123],"both":[124],"baseline":[126],"benchmark":[130],"HMM":[131],"system.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":28},{"year":2019,"cited_by_count":35},{"year":2018,"cited_by_count":38},{"year":2017,"cited_by_count":42},{"year":2016,"cited_by_count":48},{"year":2015,"cited_by_count":10}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}