{"id":"https://openalex.org/W1980652107","doi":"https://doi.org/10.1109/icassp.2014.6854053","title":"A discriminatively trained Hough Transform for frame-level phoneme recognition","display_name":"A discriminatively trained Hough Transform for frame-level phoneme recognition","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W1980652107","doi":"https://doi.org/10.1109/icassp.2014.6854053","mag":"1980652107"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5070417199","display_name":"Jonathan Dennis","orcid":null},"institutions":[{"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"]},{"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":"Jonathan Dennis","raw_affiliation_strings":["Institute for Infocomm Research, Singapore","Institute for Infocomm Research, A*STAR,Singapore,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR,Singapore,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091485423","display_name":"Huy Dat Tran","orcid":"https://orcid.org/0000-0003-0223-6140"},"institutions":[{"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"]},{"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":"Huy Dat Tran","raw_affiliation_strings":["Institute for Infocomm Research, Singapore","Institute for Infocomm Research, A*STAR,Singapore,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR,Singapore,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"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"]},{"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":"Haizhou Li","raw_affiliation_strings":["Institute for Infocomm Research, Singapore","Institute for Infocomm Research, A*STAR,Singapore,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR,Singapore,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore","Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, , Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"2514","last_page":"2518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9983000159263611,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8380515575408936},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.7803082466125488},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6578911542892456},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6291025876998901},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5875163078308105},{"id":"https://openalex.org/keywords/hough-transform","display_name":"Hough transform","score":0.539713442325592},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5334627032279968},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5136644244194031},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5078337788581848},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.4766348600387573},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4568605422973633},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.44432175159454346},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.25718092918395996}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8380515575408936},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.7803082466125488},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6578911542892456},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6291025876998901},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5875163078308105},{"id":"https://openalex.org/C200518788","wikidata":"https://www.wikidata.org/wiki/Q195076","display_name":"Hough transform","level":3,"score":0.539713442325592},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5334627032279968},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5136644244194031},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5078337788581848},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.4766348600387573},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4568605422973633},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.44432175159454346},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25718092918395996},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","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":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W22745672","https://openalex.org/W1994935303","https://openalex.org/W1995444699","https://openalex.org/W2066718061","https://openalex.org/W2095905764","https://openalex.org/W2106255337","https://openalex.org/W2119110418","https://openalex.org/W2139622435","https://openalex.org/W2147768505","https://openalex.org/W2149600041","https://openalex.org/W2160815625","https://openalex.org/W2394932179","https://openalex.org/W2402967400","https://openalex.org/W6680911068","https://openalex.org/W6711962127","https://openalex.org/W6713359473"],"related_works":["https://openalex.org/W2293149949","https://openalex.org/W2026099691","https://openalex.org/W4284672201","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2144773493"],"abstract_inverted_index":{"Despite":[0],"recent":[1],"advances":[2],"in":[3,29,62,126],"the":[4,50,63,69,75,80,91,94,104,112,115,123,130,135,141,144,156,160,174,180,184],"use":[5],"of":[6,65,71,83,86,93,103,114,143,183],"Artificial":[7],"Neural":[8],"Network":[9],"(ANN)":[10],"architectures":[11],"for":[12,68,169],"automatic":[13],"speech":[14],"recognition":[15,177],"(ASR),":[16],"relatively":[17],"little":[18],"attention":[19],"has":[20],"been":[21],"given":[22],"to":[23,39,78,90,110,121,133,152],"using":[24,45],"feature":[25,87,168],"inputs":[26],"beyond":[27],"MFCCs":[28],"such":[30,147],"systems.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35,119],"propose":[36,120],"an":[37,46,127,148],"alternative":[38],"conventional":[40],"MFCC":[41],"or":[42],"filterbank":[43],"features,":[44],"approach":[47,60],"based":[48],"on":[49,173],"Generalised":[51],"Hough":[52],"Transform":[53],"(GHT).":[54],"The":[55],"GHT":[56,161],"is":[57,77,107,132,150],"a":[58,84,99,166],"common":[59,151],"used":[61,109],"field":[64],"image":[66],"processing":[67],"task":[70,178],"object":[72],"detection,":[73],"where":[74,129],"idea":[76],"learn":[79,122],"spatial":[81],"distribution":[82],"codebook":[85,105],"information":[88],"relative":[89],"location":[92],"target":[95,116],"class.":[96],"During":[97],"recognition,":[98],"simple":[100],"weighted":[101],"summation":[102],"activations":[106,158],"commonly":[108],"detect":[111],"presence":[113],"classes.":[117],"Here":[118],"weighting":[124],"discriminatively":[125],"ANN,":[128],"aim":[131],"optimise":[134],"static":[136],"phone":[137],"classification":[138],"error":[139],"at":[140],"output":[142,157],"network.":[145],"As":[146],"ANN":[149],"hybrid":[153],"ASR":[154],"architectures,":[155],"from":[159],"can":[162],"be":[163],"considered":[164],"as":[165],"novel":[167],"ASR.":[170],"Experimental":[171],"results":[172],"TIMIT":[175],"phoneme":[176],"demonstrate":[179],"state-of-the-art":[181],"performance":[182],"approach.":[185]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}