{"id":"https://openalex.org/W2395700867","doi":"https://doi.org/10.21437/interspeech.2015-123","title":"Minimum trajectory error training for deep neural networks, combined with stacked bottleneck features","display_name":"Minimum trajectory error training for deep neural networks, combined with stacked bottleneck features","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2395700867","doi":"https://doi.org/10.21437/interspeech.2015-123","mag":"2395700867"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-123","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102765381","display_name":"Zhizheng Wu","orcid":"https://orcid.org/0009-0001-1192-9857"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhizheng Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simon King","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":false,"cited_by_count":24,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"309","last_page":"313"},"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":0.9983999729156494,"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":0.9950000047683716,"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":0.8003196716308594},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7514909505844116},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.74433434009552},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6518937349319458},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6326860189437866},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6125756502151489},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5923858880996704},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5562039613723755},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5441585183143616},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5416048765182495},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5362647771835327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4759647250175476},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.42819511890411377},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4168752431869507},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11639666557312012}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8003196716308594},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7514909505844116},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.74433434009552},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6518937349319458},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6326860189437866},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6125756502151489},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5923858880996704},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5562039613723755},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5441585183143616},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5416048765182495},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5362647771835327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4759647250175476},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.42819511890411377},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4168752431869507},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11639666557312012},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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},{"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-123","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W181329206","https://openalex.org/W1498436455","https://openalex.org/W1499332833","https://openalex.org/W1544516254","https://openalex.org/W1979449467","https://openalex.org/W1987992317","https://openalex.org/W1990505856","https://openalex.org/W2000513720","https://openalex.org/W2020024436","https://openalex.org/W2045158511","https://openalex.org/W2049686551","https://openalex.org/W2102003408","https://openalex.org/W2111194146","https://openalex.org/W2129142580","https://openalex.org/W2154920538","https://openalex.org/W2160815625","https://openalex.org/W2294246205","https://openalex.org/W2294797155"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W1984347656","https://openalex.org/W2535215250","https://openalex.org/W2024201202"],"abstract_inverted_index":{"Recently,":[0],"Deep":[1],"Neural":[2],"Networks":[3],"(DNNs)":[4],"have":[5],"shown":[6],"promise":[7],"as":[8],"an":[9],"acoustic":[10,27,91],"model":[11,131],"for":[12,129],"statistical":[13],"parametric":[14],"speech":[15,35,65,79],"synthesis.":[16],"Their":[17],"ability":[18],"to":[19,26,45],"learn":[20],"complex":[21],"mappings":[22],"from":[23,88],"linguistic":[24,113],"features":[25,28],"has":[29],"advanced":[30],"the":[31,47,56,59,122,125],"naturalness":[32,134],"of":[33,51,64,124,135],"synthesis":[34],"significantly.":[36],"However,":[37],"because":[38],"DNN":[39],"parameter":[40,80],"estimation":[41],"methods":[42],"typically":[43],"attempt":[44],"minimise":[46],"mean":[48],"squared":[49],"error":[50],"each":[52],"individual":[53],"frame":[54],"in":[55],"training":[57,75,101,127],"data,":[58],"dynamic":[60,86],"and":[61,83,117,133],"continuous":[62],"nature":[63],"parameters":[66],"is":[67],"neglected.":[68],"In":[69],"this":[70,99],"paper,":[71],"we":[72],"propose":[73],"a":[74,89],"criterion":[76,102,128],"that":[77],"minimises":[78],"trajectory":[81],"errors,":[82],"so":[84],"takes":[85],"constraints":[87],"wide":[90,112],"context":[92],"into":[93],"account":[94],"during":[95],"training.":[96],"We":[97],"combine":[98],"novel":[100],"with":[103],"our":[104],"previously":[105],"proposed":[106,126],"stacked":[107],"bottleneck":[108],"features,":[109],"which":[110],"provide":[111],"context.":[114],"Both":[115],"objective":[116],"subjective":[118],"evaluation":[119],"results":[120],"confirm":[121],"effectiveness":[123],"improving":[130],"accuracy":[132],"synthesised":[136],"speech.":[137]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":12}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}