{"id":"https://openalex.org/W1993464248","doi":"https://doi.org/10.1109/taslp.2015.2459599","title":"Generalised Hough Transform for Speech Pattern Classification","display_name":"Generalised Hough Transform for Speech Pattern Classification","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W1993464248","doi":"https://doi.org/10.1109/taslp.2015.2459599","mag":"1993464248"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2015.2459599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2459599","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":null,"license_id":null,"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":["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/A5070417199","display_name":"Jonathan Dennis","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Jonathan Dennis","raw_affiliation_strings":["A STAR Institute for Infocomm Research, Singapore","A $\\\\ast$ STAR Institute for Infocomm Research , Singapore"],"affiliations":[{"raw_affiliation_string":"A STAR Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"A $\\\\ast$ STAR Institute for Infocomm Research , Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045727408","display_name":"Dat Tran","orcid":"https://orcid.org/0009-0005-1659-5445"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tran Dat","raw_affiliation_strings":["A $\\\\ast$ STAR Institute for Infocomm Research , Singapore"],"affiliations":[{"raw_affiliation_string":"A $\\\\ast$ STAR Institute for Infocomm Research , Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["A STAR Institute for Infocomm Research, Singapore","A $\\\\ast$ STAR Institute for Infocomm Research , Singapore"],"affiliations":[{"raw_affiliation_string":"A STAR Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"A $\\\\ast$ STAR Institute for Infocomm Research , Singapore","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070417199"],"corresponding_institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":0.5744,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66312966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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":0.9976000189781189,"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":0.7904385328292847},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5967122316360474},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5705921053886414},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5679782629013062},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5661728978157043},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5636899471282959},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5630617141723633},{"id":"https://openalex.org/keywords/hough-transform","display_name":"Hough transform","score":0.5500874519348145},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5126975774765015},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43194079399108887},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.4280398488044739},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.34153425693511963},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10680878162384033}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7904385328292847},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5967122316360474},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5705921053886414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5679782629013062},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5661728978157043},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5636899471282959},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5630617141723633},{"id":"https://openalex.org/C200518788","wikidata":"https://www.wikidata.org/wiki/Q195076","display_name":"Hough transform","level":3,"score":0.5500874519348145},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5126975774765015},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43194079399108887},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.4280398488044739},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.34153425693511963},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10680878162384033},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2015.2459599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2459599","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W22745672","https://openalex.org/W111481704","https://openalex.org/W190289757","https://openalex.org/W943204654","https://openalex.org/W1533861849","https://openalex.org/W1970026646","https://openalex.org/W1975292803","https://openalex.org/W1981655197","https://openalex.org/W1994935303","https://openalex.org/W1995444699","https://openalex.org/W2005122913","https://openalex.org/W2005708641","https://openalex.org/W2046972719","https://openalex.org/W2075973450","https://openalex.org/W2090431713","https://openalex.org/W2095905764","https://openalex.org/W2106255337","https://openalex.org/W2106939211","https://openalex.org/W2108036388","https://openalex.org/W2119110418","https://openalex.org/W2124386111","https://openalex.org/W2137919539","https://openalex.org/W2139622435","https://openalex.org/W2147768505","https://openalex.org/W2149600041","https://openalex.org/W2160815625","https://openalex.org/W2165712214","https://openalex.org/W2169053895","https://openalex.org/W2184045248","https://openalex.org/W2186582651","https://openalex.org/W2394932179","https://openalex.org/W2402967400","https://openalex.org/W2404206164","https://openalex.org/W6607679263","https://openalex.org/W6631943919","https://openalex.org/W6680911068","https://openalex.org/W6711962127","https://openalex.org/W6713359473"],"related_works":["https://openalex.org/W80423236","https://openalex.org/W2155033763","https://openalex.org/W3134920593","https://openalex.org/W1990589093","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2148099973","https://openalex.org/W2340308015","https://openalex.org/W2083296885"],"abstract_inverted_index":{"While":[0],"typical":[1],"hybrid":[2],"neural":[3,114,168],"network":[4,141,169],"architectures":[5],"for":[6],"automatic":[7],"speech":[8,92,196],"recognition":[9,225],"(ASR)":[10],"use":[11,112],"a":[12,46,82,106,113,215,222,239],"context":[13],"window":[14],"of":[15,67,91,105,125,133,139,151,158,211,231],"frame-based":[16],"features,":[17],"this":[18,42],"may":[19],"not":[20],"be":[21],"the":[22,27,51,58,65,75,88,95,101,120,126,134,137,140,143,159,186,203,209,212,229,232],"best":[23],"approach":[24,153,213,233],"to":[25,111,128,166,234],"capture":[26,235],"wider":[28,96],"temporal":[29,97,241],"context,":[30],"which":[31,80,172,207,227],"contains":[32],"phonetic":[33,236],"and":[34,53],"linguistic":[35],"information":[36,56,93,237],"that":[37,48,85,155,180],"is":[38,81,154,161,188,202,221],"equally":[39],"important.":[40],"In":[41,70],"paper,":[43],"we":[44,72,109],"introduce":[45],"system":[47],"integrates":[49],"both":[50],"spectral":[52],"geometrical":[54,89],"shape":[55],"from":[57,119],"acoustic":[59],"spectrum,":[60],"inspired":[61],"by":[62],"research":[63],"in":[64],"field":[66],"machine":[68],"vision.":[69],"particular,":[71],"focus":[73],"on":[74,194,214],"Generalized":[76],"Hough":[77,122],"Transform":[78],"(GHT),":[79],"sophisticated":[83],"technique":[84],"can":[86],"model":[87],"distribution":[90],"over":[94],"context.":[98,242],"To":[99],"integrate":[100],"GHT":[102,135,160],"as":[103,176],"part":[104],"hybrid-ASR":[107],"system,":[108],"propose":[110],"network,":[115],"with":[116],"features":[117],"derived":[118],"probabilistic":[121],"voting":[123],"step":[124,157],"GHT,":[127],"implement":[129],"an":[130],"improved":[131],"version":[132],"where":[136],"output":[138,187],"represents":[142],"conventional":[144],"target":[145],"class":[146],"posteriors.":[147],"A":[148],"major":[149],"advantage":[150],"our":[152],"each":[156],"highly":[162],"interpretable,":[163],"particularly":[164],"compared":[165],"deep":[167],"(DNN)":[170],"systems":[171],"are":[173,191],"commonly":[174],"treated":[175],"powerful":[177],"black-box":[178],"classifiers":[179],"give":[181],"little":[182],"insight":[183],"into":[184],"how":[185],"achieved.":[189],"Experiments":[190],"carried":[192],"out":[193],"two":[195],"pattern":[197],"classification":[198],"tasks.":[199],"The":[200,219],"first":[201],"TIMIT":[204],"phoneme":[205],"classification,":[206],"demonstrates":[208],"performance":[210],"standard":[216],"ASR":[217],"task.":[218],"second":[220],"spoken":[223],"word":[224],"challenge,":[226],"highlights":[228],"flexibility":[230],"within":[238],"longer":[240]},"counts_by_year":[{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}