{"id":"https://openalex.org/W3096262326","doi":"https://doi.org/10.21437/interspeech.2020-2731","title":"Exploration of End-to-End Synthesisers for Zero Resource Speech Challenge 2020","display_name":"Exploration of End-to-End Synthesisers for Zero Resource Speech Challenge 2020","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096262326","doi":"https://doi.org/10.21437/interspeech.2020-2731","mag":"3096262326"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2731","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"article","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/A5113960332","display_name":"Karthik Pandia D S","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Karthik Pandia D.S.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091337351","display_name":"Anusha Prakash","orcid":"https://orcid.org/0000-0001-7913-9336"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anusha Prakash","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075941856","display_name":"Mano Ranjith Kumar M.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mano Ranjith Kumar M.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032418366","display_name":"Hema A. Murthy","orcid":"https://orcid.org/0000-0003-3611-6550"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hema A. Murthy","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113960332"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5302,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73424975,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4841","last_page":"4845"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9961000084877014,"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":0.9932000041007996,"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/spectrogram","display_name":"Spectrogram","score":0.8915252089500427},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7739750146865845},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6328966021537781},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6280233860015869},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5336649417877197},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4601607322692871},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4501660466194153},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.44238099455833435},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4335399270057678},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3672488033771515},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3260585069656372},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3184087872505188},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10574027895927429}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8915252089500427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7739750146865845},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6328966021537781},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6280233860015869},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5336649417877197},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4601607322692871},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4501660466194153},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.44238099455833435},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4335399270057678},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3672488033771515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3260585069656372},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3184087872505188},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10574027895927429},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2731","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1796128977","https://openalex.org/W1967924372","https://openalex.org/W2015876361","https://openalex.org/W2100768664","https://openalex.org/W2335906338","https://openalex.org/W2347098582","https://openalex.org/W2402146185","https://openalex.org/W2547039119","https://openalex.org/W2598638573","https://openalex.org/W2947445680","https://openalex.org/W2949382160","https://openalex.org/W2963300588","https://openalex.org/W2972867623","https://openalex.org/W2972964185"],"related_works":["https://openalex.org/W2998781440","https://openalex.org/W1840351222","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W1909292483","https://openalex.org/W1428730622","https://openalex.org/W1658560081","https://openalex.org/W2146616055","https://openalex.org/W2899676847"],"abstract_inverted_index":{"A":[0],"Spoken":[1],"dialogue":[2],"system":[3],"for":[4,19,22],"an":[5],"unseen":[6],"language":[7],"is":[8,16,33,50,68,88],"referred":[9],"to":[10,89,117,123,129,145],"as":[11,52],"Zero":[12,29],"resource":[13,30,96],"speech.":[14],"It":[15],"especially":[17],"beneficial":[18],"developing":[20],"applications":[21],"languages":[23],"that":[24,165],"have":[25],"low":[26],"digital":[27],"resources.":[28],"speech":[31,49,124],"synthesis":[32,92,169],"the":[34,42,74,91,105,130,138,147,156,160],"task":[35],"of":[36,44,55,65,85,94,108,155],"building":[37],"text-to-speech":[38],"(TTS)":[39],"models":[40,79],"in":[41,159],"absence":[43],"transcriptions.":[45],"In":[46],"this":[47,86],"work,":[48],"modelled":[51],"a":[53,62],"sequence":[54,116],"transient":[56],"and":[57,61,120,151],"steady-state":[58],"acoustic":[59,66,75],"units,":[60],"unique":[63],"set":[64],"units":[67],"discovered":[69],"by":[70,114],"iterative":[71],"training.":[72],"Using":[73],"unit":[76,111,115],"sequence,":[77],"TTS":[78,97],"are":[80,102,127],"trained.":[81],"The":[82],"main":[83],"goal":[84],"work":[87],"improve":[90,146],"quality":[93,168],"zero":[95],"system.":[98],"Four":[99],"different":[100],"systems":[101,106,158],"proposed.":[103],"All":[104],"consist":[107],"three":[109],"stages:":[110],"discovery,":[112],"followed":[113],"spectrogram":[118,122,131],"mapping,":[119,148],"finally":[121],"inversion.":[125],"Modifications":[126],"proposed":[128,157],"mapping":[132,139],"stage.":[133],"These":[134],"modifications":[135],"include":[136],"training":[137],"on":[140],"voice":[141],"data,":[142],"using":[143],"x-vectors":[144],"two-stage":[149],"learning,":[150],"gender-specific":[152],"modelling.":[153],"Evaluation":[154],"Zerospeech":[161],"2020":[162],"challenge":[163],"shows":[164],"quite":[166],"good":[167],"can":[170],"be":[171],"achieved.":[172]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
