{"id":"https://openalex.org/W2159750991","doi":"https://doi.org/10.1109/icassp.2011.5947485","title":"MLP based phoneme detectors for Automatic Speech Recognition","display_name":"MLP based phoneme detectors for Automatic Speech Recognition","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2159750991","doi":"https://doi.org/10.1109/icassp.2011.5947485","mag":"2159750991"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947485","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":["Johns Hopkins University, Baltimore, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111455517","display_name":"Patrick Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Nguyen","raw_affiliation_strings":["Microsoft Corporation, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069954850","display_name":"Geoffrey Zweig","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Geoffrey Zweig","raw_affiliation_strings":["Microsoft Corporation, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042260050","display_name":"Hynek He\u0159mansk\u00fd","orcid":"https://orcid.org/0000-0001-8032-4811"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hynek Hermansky","raw_affiliation_strings":["Johns Hopkins University, Baltimore, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101787514"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":1.7103,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.87329155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5024","last_page":"5027"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9994000196456909,"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":0.7801908254623413},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7571017742156982},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.6987431645393372},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.6552129983901978},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5643843412399292},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.47617286443710327},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.47560247778892517},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44016045331954956},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.43852126598358154},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42853862047195435},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.42071765661239624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38262230157852173},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22170940041542053},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0681270956993103}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7801908254623413},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7571017742156982},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6987431645393372},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.6552129983901978},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5643843412399292},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.47617286443710327},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.47560247778892517},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44016045331954956},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.43852126598358154},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42853862047195435},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.42071765661239624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38262230157852173},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22170940041542053},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0681270956993103},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5947485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947485","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W89824565","https://openalex.org/W178496478","https://openalex.org/W1553004968","https://openalex.org/W2095635231","https://openalex.org/W2098318492","https://openalex.org/W2105897600","https://openalex.org/W2126315862","https://openalex.org/W2131033001","https://openalex.org/W2151660570","https://openalex.org/W2158420521","https://openalex.org/W2165712214","https://openalex.org/W2166339243","https://openalex.org/W2170580867","https://openalex.org/W6603662750","https://openalex.org/W6607261905","https://openalex.org/W6632891567","https://openalex.org/W6678958850","https://openalex.org/W6684639509"],"related_works":["https://openalex.org/W2138029428","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W642007152","https://openalex.org/W2341426843","https://openalex.org/W2131711534"],"abstract_inverted_index":{"Phoneme":[0],"posterior":[1],"probabilities":[2],"estimated":[3],"using":[4],"Multi-Layer":[5],"Perceptrons":[6],"(MLPs)":[7],"are":[8,68],"extensively":[9],"used":[10,69],"both":[11,57],"as":[12,31],"acoustic":[13,53,58],"scores":[14],"and":[15,59],"features":[16],"for":[17,35],"speech":[18,36,82],"recognition.":[19,37],"In":[20],"this":[21],"paper":[22],"we":[23],"explore":[24],"a":[25],"different":[26],"application":[27],"of":[28,81],"these":[29,41],"posteriors":[30],"phonetic":[32,49,60],"event":[33,66],"detectors":[34,42,67],"We":[38],"show":[39],"how":[40],"can":[43],"be":[44],"built":[45],"to":[46,77],"reliably":[47],"capture":[48],"events":[50],"in":[51],"the":[52,79,86],"signal":[54],"by":[55],"integrating":[56],"information":[61],"about":[62],"sound":[63],"classes.":[64],"These":[65],"along":[70],"with":[71],"Segmental":[72],"Conditional":[73],"Random":[74],"Fields":[75],"(SCRFs)":[76],"improve":[78],"performance":[80],"recognition":[83],"systems":[84],"on":[85],"Broadcast":[87],"News":[88],"task.":[89]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}