{"id":"https://openalex.org/W2747192917","doi":"https://doi.org/10.21437/interspeech.2017-1476","title":"Unsupervised Speech Signal to Symbol Transformation for Zero Resource Speech Applications","display_name":"Unsupervised Speech Signal to Symbol Transformation for Zero Resource Speech Applications","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2747192917","doi":"https://doi.org/10.21437/interspeech.2017-1476","mag":"2747192917"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1476","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/A5045247662","display_name":"Saurabhchand Bhati","orcid":"https://orcid.org/0000-0001-6477-3895"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Saurabhchand Bhati","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001110193","display_name":"Shekhar Nayak","orcid":"https://orcid.org/0000-0002-4277-4851"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shekhar Nayak","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5067617924","display_name":"K. Sri Rama Murty","orcid":"https://orcid.org/0000-0002-6355-5287"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"K. Sri Rama Murty","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045247662"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6612,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.8819037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2133","last_page":"2137"},"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":0.9984999895095825,"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":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8223583102226257},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6290554404258728},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6188845634460449},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5404040217399597},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.49906325340270996},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.49488896131515503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4911946952342987},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4377824366092682},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.42094454169273376},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41952812671661377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8223583102226257},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6290554404258728},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6188845634460449},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5404040217399597},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.49906325340270996},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.49488896131515503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4911946952342987},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4377824366092682},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.42094454169273376},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41952812671661377},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2017-1476","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:raiith.iith.ac.in:5161","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400292","display_name":"Research Archive of Indian Institute of Technology Hyderabad (Indian Institute of Technology Hyderabad)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I65181880","host_organization_name":"Indian Institute of Technology Hyderabad","host_organization_lineage":["https://openalex.org/I65181880"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:raiith.iith.ac.in:7788","is_oa":false,"landing_page_url":"http://raiith.iith.ac.in/7788/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400292","display_name":"Research Archive of Indian Institute of Technology Hyderabad (Indian Institute of Technology Hyderabad)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I65181880","host_organization_name":"Indian Institute of Technology Hyderabad","host_organization_lineage":["https://openalex.org/I65181880"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1673310716","https://openalex.org/W1796128977","https://openalex.org/W2017257315","https://openalex.org/W2020607164","https://openalex.org/W2025543856","https://openalex.org/W2078769636","https://openalex.org/W2079460648","https://openalex.org/W2100308344","https://openalex.org/W2100768664","https://openalex.org/W2117041980","https://openalex.org/W2121997342","https://openalex.org/W2126203737","https://openalex.org/W2140991203","https://openalex.org/W2160815625","https://openalex.org/W2170659185","https://openalex.org/W2251025892","https://openalex.org/W2346964103","https://openalex.org/W2395899413","https://openalex.org/W2398490608","https://openalex.org/W2399576818","https://openalex.org/W2400549570","https://openalex.org/W2402366697","https://openalex.org/W2406349064","https://openalex.org/W2407614114"],"related_works":["https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2370205415","https://openalex.org/W4387493491","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W2904225411","https://openalex.org/W4388331409","https://openalex.org/W2393816671"],"abstract_inverted_index":{"Zero":[0],"resource":[1,27,140,173],"speech":[2,28,44,141],"processing":[3],"refers":[4],"to":[5,25,110,119],"a":[6,21,51,67,80,93,103],"scenario":[7],"where":[8],"no":[9],"or":[10],"minimal":[11],"transcribed":[12],"data":[13],"is":[14,108,149,177],"available.":[15],"In":[16,37,99],"this":[17],"paper,":[18],"we":[19,41],"propose":[20],"three-step":[22],"unsupervised":[23,84],"approach":[24,148],"zero":[26,139,172],"processing,":[29],"which":[30],"does":[31],"not":[32],"require":[33],"any":[34,194],"other":[35],"information/dataset.":[36],"the":[38,43,63,100,112,117,131,138,146,180,187,191],"first":[39],"step,":[40,102],"segment":[42,75],"signal":[45,118],"into":[46,66],"phonemelike":[47],"units,":[48],"resulting":[49],"in":[50,137,189],"large":[52],"number":[53,69],"of":[54,70,91,95,145,171],"varying":[55],"length":[56],"segments.":[57],"The":[58,83,125,143],"second":[59],"step":[60],"involves":[61],"clustering":[62],"varying-length":[64],"segments":[65],"finite":[68],"clusters":[71],"so":[72],"that":[73,179],"each":[74],"can":[76,88],"be":[77,89],"labeled":[78],"with":[79],"cluster":[81],"index.":[82],"transcriptions,":[85],"thus":[86],"obtained,":[87],"thought":[90],"as":[92,135,169],"sequence":[94],"virtual":[96,122,126],"phone":[97,123,127],"labels.":[98],"third":[101],"deep":[104],"neural":[105],"network":[106],"classifier":[107],"trained":[109],"map":[111],"feature":[113],"vectors":[114],"extracted":[115,129],"from":[116,130],"its":[120],"corresponding":[121],"label.":[124],"posteriors":[128],"DNN":[132],"are":[133],"used":[134],"features":[136],"processing.":[142],"effectiveness":[144],"proposed":[147,181],"evaluated":[150],"on":[151],"both":[152,190],"ABX":[153],"and":[154,164],"spoken":[155],"term":[156],"discovery":[157],"tasks":[158,192],"(STD)":[159],"using":[160],"spontaneous":[161],"American":[162],"English":[163],"Tsonga":[165],"language":[166],"datasets,":[167,188],"provided":[168],"part":[170],"2015":[174],"challenge.":[175],"It":[176],"observed":[178],"system":[182],"outperforms":[183],"baselines,":[184],"supplied":[185],"along":[186],"without":[193],"task":[195],"specific":[196],"modifications":[197]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}