{"id":"https://openalex.org/W2102264166","doi":"https://doi.org/10.21437/interspeech.2010-383","title":"A comparative large scale study of MLP features for Mandarin ASR","display_name":"A comparative large scale study of MLP features for Mandarin ASR","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W2102264166","doi":"https://doi.org/10.21437/interspeech.2010-383","mag":"2102264166"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-383","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-383","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://publications.rwth-aachen.de/search?p=id:%22RWTH-CONV-196169%22","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":true,"raw_author_name":"Fabio Valente","raw_affiliation_strings":["Idiap Research Institute, Martigny-Combe, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny-Combe, 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-Combe, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny-Combe, 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":["RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Aachen, Germany","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/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suman V. Ravuri","raw_affiliation_strings":["University of California, Berkeley, Berkeley, United States"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, United States","institution_ids":["https://openalex.org/I95457486"]}]},{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["SRI International, Menlo Park, United States"],"affiliations":[{"raw_affiliation_string":"SRI International, Menlo Park, United States","institution_ids":["https://openalex.org/I1298353152"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5061495800"],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":4.645,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.94754709,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9994999766349792,"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/T11698","display_name":"Underwater Acoustics Research","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8479275703430176},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8286580443382263},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7966327667236328},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7053788900375366},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.6454818248748779},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5762418508529663},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.574170708656311},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5727083086967468},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5551057457923889},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5267906785011292},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5244401097297668},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4686878025531769},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3925116956233978}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8479275703430176},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8286580443382263},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7966327667236328},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7053788900375366},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.6454818248748779},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5762418508529663},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.574170708656311},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5727083086967468},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5551057457923889},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5267906785011292},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5244401097297668},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4686878025531769},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3925116956233978},{"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},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2010-383","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-383","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.rwth-aachen.de:125721","is_oa":true,"landing_page_url":"https://publications.rwth-aachen.de/record/125721","pdf_url":"https://publications.rwth-aachen.de/search?p=id:%22RWTH-CONV-196169%22","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":"Proceedings of the 11th Annual Conference of the International Speech Communication Association, (Interspeech 2010) : 26 - 30 September, 2010, Makuhari, Chiba, Japan<br/>11. Annual Conference of the International Speech Communication Association, Interspeech 2010, Chhiba, Japan, 2010-09-26 - 2010-09-30","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.174.8251","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.174.8251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-i6.informatik.rwth-aachen.de/publications/download/680/Valente-Interspeech-2010.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.232.6710","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.232.6710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.speech.sri.com/papers/interspeech2010-mlpcompare.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:publications.rwth-aachen.de:125721","is_oa":true,"landing_page_url":"https://publications.rwth-aachen.de/record/125721","pdf_url":"https://publications.rwth-aachen.de/search?p=id:%22RWTH-CONV-196169%22","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":"Proceedings of the 11th Annual Conference of the International Speech Communication Association, (Interspeech 2010) : 26 - 30 September, 2010, Makuhari, Chiba, Japan<br/>11. Annual Conference of the International Speech Communication Association, Interspeech 2010, Chhiba, Japan, 2010-09-26 - 2010-09-30","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2102264166.pdf","grobid_xml":"https://content.openalex.org/works/W2102264166.grobid-xml"},"referenced_works_count":18,"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/W1495547083","https://openalex.org/W1517381888","https://openalex.org/W1920478749","https://openalex.org/W2071489795","https://openalex.org/W2096215262","https://openalex.org/W2101596234","https://openalex.org/W2141499240","https://openalex.org/W2144071798","https://openalex.org/W2144663079","https://openalex.org/W2165712214","https://openalex.org/W2167423437","https://openalex.org/W2805889152"],"related_works":["https://openalex.org/W2990982991","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/W4286643620","https://openalex.org/W2523437662"],"abstract_inverted_index":{"MLP":[0,20,89,133],"based":[1,119],"front-ends":[2],"have":[3],"shown":[4],"significant":[5],"complementary":[6],"properties":[7],"to":[8,59,114],"conventional":[9,116],"spectral":[10,118],"features.":[11],"As":[12],"part":[13],"of":[14,45,50,53,79,98,108],"the":[15,31,43,51,83,88,96,105,115],"DARPA":[16],"GALE":[17,84],"program,":[18],"different":[19,106],"features":[21,47,90,120],"were":[22],"developed":[23],"for":[24],"Mandarin":[25],"ASR.":[26],"In":[27],"this":[28],"paper,":[29],"all":[30],"proposed":[32],"frontends":[33],"are":[34],"compared":[35,113],"in":[36,48,95],"systematic":[37],"manner":[38],"and":[39,62,72,123],"we":[40],"extensively":[41],"investigate":[42],"scalability":[44],"these":[46],"terms":[49],"amount":[52],"training":[54],"data":[55,81],"(from":[56],"100":[57],"hours":[58,78],"1600":[60],"hours)":[61],"system":[63,111],"complexity":[64],"(maximum":[65],"likelihood":[66],"training,":[67],"SAT,":[68],"lattice":[69],"level":[70],"combination,":[71],"discriminative":[73],"training).":[74],"Results":[75],"on":[76],"5":[77],"evaluation":[80],"from":[82],"project":[85],"reveal":[86],"that":[87],"consistently":[91],"produce":[92],"relative":[93],"improvements":[94],"range":[97],"15":[99],"%":[100,103],"\u2212":[101],"23":[102],"at":[104],"steps":[107],"a":[109,131],"multipass":[110],"when":[112],"short-term":[117],"like":[121],"MFCC":[122],"PLP.":[124],"The":[125],"largest":[126],"improvement":[127],"is":[128],"obtained":[129],"using":[130],"hierarchical":[132],"approach.":[134]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}