{"id":"https://openalex.org/W2119531180","doi":"https://doi.org/10.1109/tasl.2011.2139206","title":"Transcribing Mandarin Broadcast Speech Using Multi-Layer Perceptron Acoustic Features","display_name":"Transcribing Mandarin Broadcast Speech Using Multi-Layer Perceptron Acoustic Features","publication_year":2011,"publication_date":"2011-04-26","ids":{"openalex":"https://openalex.org/W2119531180","doi":"https://doi.org/10.1109/tasl.2011.2139206","mag":"2119531180"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2011.2139206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2139206","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/192683","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061495800","display_name":"Fabio Valente","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Fabio Valente","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043551083","display_name":"Mathew Magimai.-Doss","orcid":"https://orcid.org/0000-0002-8714-1409"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mathew Magimai Doss","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062688417","display_name":"Christian Plahl","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Plahl","raw_affiliation_strings":["Computer Science Department, RWTH Aachen University, Aachen, Germany","Comput. Sci. Dept., RWTH Aachen Univ., Aachen, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Comput. Sci. Dept., RWTH Aachen Univ., Aachen, Germany#TAB#","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026262869","display_name":"Suman Ravuri","orcid":"https://orcid.org/0000-0002-7481-7633"},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suman Ravuri","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA","Int. Comput. Sci. Inst., Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"Int. Comput. Sci. Inst., Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066920453","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0003-2950-693X"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5367,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83496884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"19","issue":"8","first_page":"2439","last_page":"2450"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994000196456909,"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":0.9886999726295471,"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":0.8078171014785767},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7922772169113159},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7296708822250366},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.7246603965759277},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.6690922975540161},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6446752548217773},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5917492508888245},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5377208590507507},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5169350504875183},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4967944920063019},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4779374897480011},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.44842416048049927},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4249141216278076},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3875429630279541},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.32946062088012695},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11919781565666199}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8078171014785767},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7922772169113159},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7296708822250366},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.7246603965759277},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.6690922975540161},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6446752548217773},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5917492508888245},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5377208590507507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5169350504875183},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4967944920063019},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4779374897480011},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.44842416048049927},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4249141216278076},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3875429630279541},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32946062088012695},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11919781565666199},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","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:10.1109/tasl.2011.2139206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2139206","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:infoscience.epfl.ch:192683","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192683","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:publications.rwth-aachen.de:187572","is_oa":false,"landing_page_url":"https://publications.rwth-aachen.de/record/187572","pdf_url":null,"source":{"id":"https://openalex.org/S4306401362","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE transactions on audio, speech and language processing : T-ASL 19(8), 2439-2450 (2011). doi:10.1109/TASL.2011.2139206","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:192683","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192683","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W89824565","https://openalex.org/W103244930","https://openalex.org/W132821814","https://openalex.org/W158407117","https://openalex.org/W197151588","https://openalex.org/W336107121","https://openalex.org/W811578723","https://openalex.org/W1484387534","https://openalex.org/W1517381888","https://openalex.org/W1522045018","https://openalex.org/W1553004968","https://openalex.org/W1588471869","https://openalex.org/W1920478749","https://openalex.org/W2012897754","https://openalex.org/W2046331056","https://openalex.org/W2071489795","https://openalex.org/W2075036909","https://openalex.org/W2096215262","https://openalex.org/W2101596234","https://openalex.org/W2140017413","https://openalex.org/W2141499240","https://openalex.org/W2142694085","https://openalex.org/W2144663079","https://openalex.org/W2152060930","https://openalex.org/W2159948109","https://openalex.org/W2165712214","https://openalex.org/W2167206253","https://openalex.org/W2167513360","https://openalex.org/W2167763959","https://openalex.org/W4299602298","https://openalex.org/W6604228424","https://openalex.org/W6606465599","https://openalex.org/W6607944266","https://openalex.org/W6631255193","https://openalex.org/W6674659399","https://openalex.org/W6681386174","https://openalex.org/W6683644788","https://openalex.org/W6844396509"],"related_works":["https://openalex.org/W2120446725","https://openalex.org/W2076543106","https://openalex.org/W2111680118","https://openalex.org/W4246803324","https://openalex.org/W2019891950","https://openalex.org/W2085842814","https://openalex.org/W2159897332","https://openalex.org/W2523437662","https://openalex.org/W4387048144","https://openalex.org/W2492135063"],"abstract_inverted_index":{"Recently,":[0],"several":[1],"multi-layer":[2],"perceptron":[3],"(MLP)-based":[4],"front-ends":[5,61,141],"have":[6,92],"been":[7,45],"developed":[8,63],"and":[9,69,103,124,151,181,237,250],"used":[10,26,142],"for":[11],"Mandarin":[12,29,275],"speech":[13],"recognition,":[14],"often":[15],"showing":[16],"significant":[17],"complementary":[18],"properties":[19],"to":[20,100,163,178,232,273],"conventional":[21],"spectral":[22],"features.":[23],"Although":[24],"widely":[25],"in":[27,71,119,143,155,161,167,216],"multiple":[28,65],"systems,":[30],"no":[31],"systematic":[32,73],"comparison":[33,135],"of":[34,49,96,106,121,130,169,172,201,219,226,248,254,259],"all":[35,58],"the":[36,59,83,89,94,101,104,112,125,134,138,144,170,182,205,210,217,223,242,246,252,255,263],"different":[37,97,224],"approaches":[38],"as":[39,41,149],"well":[40],"their":[42,165],"scalability":[43,166],"has":[44],"proposed.":[46],"The":[47,80,115,257],"novelty":[48],"this":[50,56],"correspondence":[51],"is":[52],"mainly":[53],"experimental.":[54],"In":[55],"work,":[57],"MLP":[60,90,102,109,211],"recently":[62],"at":[64,222],"sites":[66],"are":[67,117,153],"described":[68],"compared":[70,231,272],"a":[72,76,128,156,227],"manner":[74],"on":[75,198],"100":[77,176],"hours":[78,177,200],"setup.":[79],"study":[81],"covers":[82],"two":[84,139],"main":[85],"directions":[86],"along":[87],"which":[88],"features":[91,212,261],"evolved:":[93],"use":[95,105],"input":[98],"representations":[99],"more":[107,157],"complex":[108,158],"architectures":[110],"beyond":[111],"three-layer":[113],"perceptron.":[114],"results":[116],"analyzed":[118],"terms":[120,168],"confusion":[122],"matrices":[123],"paper":[126],"discusses":[127],"number":[129],"novel":[131],"findings":[132],"that":[133,209,241],"reveals.":[136],"Furthermore,":[137],"best":[140],"GALE":[145,206,264],"2008":[146,265],"evaluation,":[147],"referred":[148],"MLP1":[150],"MLP2,":[152],"studied":[154],"LVCSR":[159],"system":[160,184,229,267],"order":[162],"investigate":[164],"amount":[171,247],"training":[173],"data":[174,203,249],"(from":[175],"1600":[179],"hours)":[180],"parametric":[183],"complexity":[185,253],"(maximum":[186],"likelihood":[187],"versus":[188],"discriminative":[189],"training,":[190,193],"speaker":[191],"adaptative":[192],"lattice":[194],"level":[195],"combination).":[196],"Results":[197],"5":[199],"evaluation":[202,266],"from":[204],"project":[207],"reveal":[208],"consistently":[213],"produce":[214],"improvements":[215,243],"range":[218],"15%-23%":[220],"relative":[221],"steps":[225],"multipass":[228],"when":[230],"mel-frequency":[233],"cepstral":[234],"coefficient":[235],"(MFCC)":[236],"PLP":[238],"features,":[239],"suggesting":[240],"scale":[244],"with":[245,251],"system.":[256],"integration":[258],"those":[260],"into":[262],"provide":[268],"very":[269],"competitive":[270],"performances":[271],"other":[274],"systems.":[276]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}