{"id":"https://openalex.org/W2040731397","doi":"https://doi.org/10.1109/slt.2012.6424211","title":"Combining cepstral normalization and cochlear implant-like speech processing for microphone array-based speech recognition","display_name":"Combining cepstral normalization and cochlear implant-like speech processing for microphone array-based speech recognition","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2040731397","doi":"https://doi.org/10.1109/slt.2012.6424211","mag":"2040731397"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2012.6424211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/192389","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066876667","display_name":"Cong-Thanh Do","orcid":"https://orcid.org/0000-0003-1748-2846"},"institutions":[{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Cong-Thanh Do","raw_affiliation_strings":["LIMSI, CNRS, Orsay, France","LIMSI-CNRS, BP 133, 91403, Orsay cedex, France#TAB#"],"affiliations":[{"raw_affiliation_string":"LIMSI, CNRS, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LIMSI-CNRS, BP 133, 91403, Orsay cedex, France#TAB#","institution_ids":["https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101412090","display_name":"Mohammad J. Taghizadeh","orcid":"https://orcid.org/0000-0002-3383-2255"},"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":"Mohammad J. Taghizadeh","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","Idiap Research Institute, CH-1920 Martigny, Switzerland,#TAB#"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"Idiap Research Institute, CH-1920 Martigny, Switzerland,#TAB#","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081808619","display_name":"Philip N. Garner","orcid":"https://orcid.org/0000-0002-0814-1348"},"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":"Philip N. Garner","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","Idiap Research Institute, CH-1920 Martigny, Switzerland,#TAB#"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"Idiap Research Institute, CH-1920 Martigny, Switzerland,#TAB#","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066876667"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210115485"],"apc_list":null,"apc_paid":null,"fwci":1.9818,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.89146503,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"270","issue":null,"first_page":"137","last_page":"142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life 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"}}],"keywords":[{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.9056535959243774},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.7708323001861572},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7239243984222412},{"id":"https://openalex.org/keywords/cochlear-implant","display_name":"Cochlear implant","score":0.7195883989334106},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6763848662376404},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5920913219451904},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5157473683357239},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5054116249084473},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.264582097530365},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.19134730100631714},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.09713956713676453},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.053406596183776855},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.04798251390457153}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.9056535959243774},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.7708323001861572},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7239243984222412},{"id":"https://openalex.org/C2778882171","wikidata":"https://www.wikidata.org/wiki/Q724965","display_name":"Cochlear implant","level":2,"score":0.7195883989334106},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6763848662376404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5920913219451904},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5157473683357239},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5054116249084473},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.264582097530365},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.19134730100631714},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.09713956713676453},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.053406596183776855},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.04798251390457153},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/slt.2012.6424211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.650.9165","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.650.9165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/papers/2012/Do_SLT_2012.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:192389","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192389","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"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:192389","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192389","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/4","score":0.5199999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W290530603","https://openalex.org/W1515932869","https://openalex.org/W1967558850","https://openalex.org/W1974932989","https://openalex.org/W2033178790","https://openalex.org/W2066561607","https://openalex.org/W2069976350","https://openalex.org/W2099201661","https://openalex.org/W2099565946","https://openalex.org/W2099655464","https://openalex.org/W2113556376","https://openalex.org/W2114155159","https://openalex.org/W2116623987","https://openalex.org/W2146873606","https://openalex.org/W2149693148","https://openalex.org/W2153773386","https://openalex.org/W2158072351","https://openalex.org/W2163343350","https://openalex.org/W2168630132","https://openalex.org/W2568428461","https://openalex.org/W3141933106","https://openalex.org/W4210849719","https://openalex.org/W4249052411","https://openalex.org/W4300507149"],"related_works":["https://openalex.org/W334008168","https://openalex.org/W2396048001","https://openalex.org/W2905188205","https://openalex.org/W1559044324","https://openalex.org/W2535773091","https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W3024488226"],"abstract_inverted_index":{"This":[0,157],"paper":[1],"investigates":[2],"the":[3,42,61,71,91,111,128,140,145,185,191],"combination":[4],"of":[5,113,151],"cepstral":[6,80,101,119,155,166],"normalization":[7,84,102,120,167],"and":[8,28,35,50,73,82,86,93,121,153],"cochlear":[9,66,104,122,169],"implant-like":[10,54,105,123,170],"speech":[11,16,19,39,55,62,75,106,116,124,171],"processing":[12,63,107,125,172,182],"for":[13],"microphone":[14,26,114],"array-based":[15,115],"recognition.":[17,117],"Testing":[18],"signals":[20],"are":[21,29,48,88,137],"recorded":[22],"by":[23],"a":[24,160],"circular":[25],"array":[27],"subsequently":[30],"processed":[31],"with":[32],"superdirective":[33],"beamforming":[34],"McCowan":[36],"post-filtering.":[37],"Training":[38],"signals,":[40],"from":[41,60],"multichannel":[43],"overlapping":[44,133],"Number":[45],"corpus":[46],"(MONC),":[47],"clean":[49],"not":[51],"overlapping.":[52],"Cochlear":[53],"processing,":[56],"which":[57],"is":[58,68,132,173],"inspired":[59],"strategy":[64],"in":[65,109],"implants,":[67],"applied":[69,89],"on":[70,90],"training":[72,92,152],"testing":[74,94,154],"signals.":[76],"Cepstral":[77],"normalization,":[78],"including":[79],"mean":[81],"variance":[83],"(CMN":[85],"CVN),":[87],"cepstra.":[95],"Experiments":[96],"show":[97],"that":[98,178],"implementing":[99],"either":[100,165],"or":[103,168],"helps":[108],"reducing":[110],"WERs":[112],"Combining":[118],"reduces":[126,183],"further":[127,184],"WERs,":[129],"when":[130,164],"there":[131],"speech.":[134],"Train/test":[135],"mismatches":[136,187],"measured":[138],"using":[139],"Kullback-Leibler":[141],"divergence":[142],"(KLD),":[143],"between":[144],"global":[146],"probability":[147],"density":[148],"functions":[149],"(PDFs)":[150],"vectors.":[156],"measure":[158],"reveals":[159,176],"train/test":[161,186],"mismatch":[162],"reduction":[163],"used.":[174],"It":[175],"also":[177],"combining":[179],"these":[180],"two":[181],"as":[188,190],"well":[189],"WERs.":[192]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
