{"id":"https://openalex.org/W2274854232","doi":"https://doi.org/10.1109/taslp.2016.2551865","title":"Improving Trajectory Modelling for DNN-Based Speech Synthesis by Using Stacked Bottleneck Features and Minimum Generation Error Training","display_name":"Improving Trajectory Modelling for DNN-Based Speech Synthesis by Using Stacked Bottleneck Features and Minimum Generation Error Training","publication_year":2016,"publication_date":"2016-04-07","ids":{"openalex":"https://openalex.org/W2274854232","doi":"https://doi.org/10.1109/taslp.2016.2551865","mag":"2274854232"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2551865","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2551865","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/taslp.2016.2551865","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhizheng Wu","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":"Zhizheng Wu","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":null,"display_name":"Simon King","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":"Simon King","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, U.K","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":6.4965,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.96597544,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"24","issue":"7","first_page":"1255","last_page":"1265"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.920799970626831,"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":0.920799970626831,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.024800000712275505,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.02449999935925007,"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/bottleneck","display_name":"Bottleneck","score":0.7997999787330627},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5777999758720398},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5569000244140625},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5540000200271606},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4555000066757202},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.43470001220703125},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3725999891757965},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.3619999885559082},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.3433000147342682}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7997999787330627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7635999917984009},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5777999758720398},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5569000244140625},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5540000200271606},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5066999793052673},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4555000066757202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44670000672340393},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.43470001220703125},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3725999891757965},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.3619999885559082},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.3433000147342682},{"id":"https://openalex.org/C47702885","wikidata":"https://www.wikidata.org/wiki/Q5441227","display_name":"Feedforward neural network","level":3,"score":0.3346000015735626},{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.3330000042915344},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29739999771118164},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2935999929904938},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.25270000100135803}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2016.2551865","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2551865","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/f86f0e29-2d0d-47d9-aead-cbf4140e3595","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f86f0e29-2d0d-47d9-aead-cbf4140e3595","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Wu, Z & King, S 2016, 'Improving trajectory modelling for DNN-based speech synthesis by using stacked bottleneck features and minimum generation error training', IEEE/ACM Transactions on Audio Speech and Language Processing, vol. 24, no. 7, pp. 1255-1265. https://doi.org/10.1109/TASLP.2016.2551865","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:1602.06727","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1602.06727","pdf_url":"https://arxiv.org/pdf/1602.06727","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"}],"best_oa_location":{"id":"doi:10.1109/taslp.2016.2551865","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2551865","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1499332833","https://openalex.org/W1502723613","https://openalex.org/W1543299179","https://openalex.org/W1544516254","https://openalex.org/W1576227399","https://openalex.org/W1613141907","https://openalex.org/W1979449467","https://openalex.org/W1987992317","https://openalex.org/W1990505856","https://openalex.org/W2000513720","https://openalex.org/W2020024436","https://openalex.org/W2024490156","https://openalex.org/W2043003570","https://openalex.org/W2045158511","https://openalex.org/W2049036695","https://openalex.org/W2049686551","https://openalex.org/W2078597717","https://openalex.org/W2094721231","https://openalex.org/W2100167690","https://openalex.org/W2105099419","https://openalex.org/W2129142580","https://openalex.org/W2134973740","https://openalex.org/W2136374105","https://openalex.org/W2150658333","https://openalex.org/W2154920538","https://openalex.org/W2159948109","https://openalex.org/W2160815625","https://openalex.org/W6601233782","https://openalex.org/W6601785968","https://openalex.org/W6605453507","https://openalex.org/W6607399213","https://openalex.org/W6611766843","https://openalex.org/W6626982579","https://openalex.org/W6634201745","https://openalex.org/W6639701888","https://openalex.org/W6675380101","https://openalex.org/W6676358011","https://openalex.org/W6678292227","https://openalex.org/W6689943414","https://openalex.org/W6696843773","https://openalex.org/W6697270646","https://openalex.org/W6711832335","https://openalex.org/W6712575312","https://openalex.org/W6712820016","https://openalex.org/W6713438222","https://openalex.org/W6713766066","https://openalex.org/W6713860685","https://openalex.org/W6735542774"],"related_works":[],"abstract_inverted_index":{"We":[0,115],"propose":[1],"two":[2,105,137],"novel":[3],"techniques-stacking":[4],"bottleneck":[5,50],"features":[6],"and":[7,33,40,92,101,119],"minimum":[8],"generation":[9],"error":[10,80,88],"(MGE)":[11],"training":[12,74],"criterion-to":[13],"improve":[14,113],"the":[15,27,36,70,87,97,124,127,136],"performance":[16],"of":[17,30,35,126],"deep":[18],"neural":[19,155],"network":[20,156],"(DNN)-based":[21],"speech":[22,145],"synthesis.":[23],"The":[24,72,104,130],"techniques":[25,106,138],"address":[26],"related":[28],"issues":[29],"frame-by-frame":[31],"independence":[32],"ignorance":[34],"relationship":[37],"between":[38,99],"static":[39,100],"dynamic":[41,102],"features,":[42,51],"within":[43],"current":[44],"typical":[45],"DNN-based":[46],"synthesis":[47],"frameworks.":[48],"Stacking":[49],"which":[52],"are":[53],"an":[54,60,82],"acoustically":[55],"informed":[56],"linguistic":[57,67],"representation,":[58],"provides":[59],"efficient":[61],"way":[62],"to":[63,111,140],"include":[64],"more":[65,142],"detailed":[66],"context":[68],"at":[69],"input.":[71],"MGE":[73],"criterion":[75],"minimises":[76],"overall":[77],"output":[78],"trajectory":[79],"across":[81],"utterance,":[83],"rather":[84],"than":[85,146],"minimising":[86],"per":[89],"frame":[90],"independently,":[91],"thus":[93],"takes":[94],"into":[95],"account":[96],"interaction":[98],"features.":[103],"can":[107],"be":[108],"easily":[109],"combined":[110],"further":[112],"performance.":[114],"present":[116],"both":[117],"objective":[118],"subjective":[120,131],"results":[121,132],"that":[122,134],"demonstrate":[123],"effectiveness":[125],"proposed":[128],"techniques.":[129],"show":[133],"combining":[135],"leads":[139],"significantly":[141],"natural":[143],"synthetic":[144],"from":[147],"conventional":[148],"DNN":[149],"or":[150],"long":[151],"short-term":[152],"memory":[153],"recurrent":[154],"systems.":[157]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}