{"id":"https://openalex.org/W2168758670","doi":"https://doi.org/10.21437/eurospeech.2003-338","title":"On factorizing spectral dynamics for robust speech recognition","display_name":"On factorizing spectral dynamics for robust speech recognition","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W2168758670","doi":"https://doi.org/10.21437/eurospeech.2003-338","mag":"2168758670"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-338","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://infoscience.epfl.ch/record/82870/files/mcms_rr.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062805147","display_name":"Vivek Tyagi","orcid":"https://orcid.org/0000-0002-3067-0801"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Vivek Tyagi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072372659","display_name":"Iain McCowan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iain A. McCowan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Herv\u00e9 Bourlard","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5017720802","display_name":"Hemant Misra","orcid":"https://orcid.org/0000-0002-8179-4441"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hemant Misra","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5062805147"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4045,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.86039516,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"981","last_page":"984"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9995999932289124,"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":0.9959999918937683,"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/cepstrum","display_name":"Cepstrum","score":0.7447306513786316},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6953919529914856},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6947581171989441},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.686410665512085},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6232304573059082},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.5748015642166138},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5474338531494141},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.4713434875011444},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.448718786239624},{"id":"https://openalex.org/keywords/frequency-modulation","display_name":"Frequency modulation","score":0.4449644386768341},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4380817413330078},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4157017469406128},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3089292645454407},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.17084482312202454},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.16933315992355347},{"id":"https://openalex.org/keywords/radio-frequency","display_name":"Radio frequency","score":0.14089226722717285},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10779747366905212},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10185250639915466}],"concepts":[{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.7447306513786316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6953919529914856},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6947581171989441},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.686410665512085},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6232304573059082},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.5748015642166138},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5474338531494141},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.4713434875011444},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.448718786239624},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.4449644386768341},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4380817413330078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4157017469406128},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3089292645454407},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17084482312202454},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.16933315992355347},{"id":"https://openalex.org/C74064498","wikidata":"https://www.wikidata.org/wiki/Q3396184","display_name":"Radio frequency","level":2,"score":0.14089226722717285},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10779747366905212},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10185250639915466},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.21437/eurospeech.2003-338","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.tind.io:82870","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/228261","pdf_url":"https://infoscience.epfl.ch/record/82870/files/mcms_rr.pdf","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"report"},{"id":"pmh:oai:infoscience.tind.io:82872","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/228263","pdf_url":"http://publications.idiap.ch/downloads/reports/2003/mcms_rr.pdf","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference proceedings"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.636.6725","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.636.6725","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.idiap.ch/ftp/reports/2003/mcms_rr.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:82870","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82870","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:infoscience.epfl.ch:82872","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82872","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.tind.io:82870","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/228261","pdf_url":"https://infoscience.epfl.ch/record/82870/files/mcms_rr.pdf","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"report"},"sustainable_development_goals":[{"score":0.75,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2168758670.pdf"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W322227076","https://openalex.org/W1920962724","https://openalex.org/W1992272902","https://openalex.org/W1994396704","https://openalex.org/W2022554507","https://openalex.org/W2137075158","https://openalex.org/W2148154194","https://openalex.org/W2156602598","https://openalex.org/W4245923654","https://openalex.org/W4302815339"],"related_works":["https://openalex.org/W2990982991","https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W2160511961"],"abstract_inverted_index":{"In":[0,78],"this":[1],"paper,":[2],"we":[3],"introduce":[4],"new":[5,95],"dynamic":[6,47,96],"speech":[7,103],"features":[8,48,56,97,118],"based":[9],"on":[10],"the":[11,22,26,61,71,114],"modulation":[12,73],"spectrum.":[13],"These":[14],"features,":[15],"termed":[16],"Mel-cepstrum":[17],"Modulation":[18],"Spectrum":[19],"(MCMS),":[20],"map":[21],"time":[23],"trajectories":[24],"of":[25,32,46,63,66,76],"spectral":[27],"dynamics":[28],"into":[29],"a":[30,40,88,99],"series":[31],"slow":[33],"and":[34,43,52,119],"fast":[35],"moving":[36],"orthogonal":[37],"components,":[38],"providing":[39,87],"more":[41],"general":[42],"discriminative":[44],"range":[45,75],"than":[49],"traditional":[50],"delta":[51],"acceleration":[53],"features.":[54,121],"The":[55],"can":[57],"be":[58],"seen":[59],"as":[60,84,86],"outputs":[62],"an":[64],"array":[65],"band-pass":[67],"filters":[68],"spread":[69],"over":[70],"cepstral":[72],"frequency":[74],"interest.":[77],"experiments,":[79],"it":[80],"is":[81],"shown":[82],"that,":[83],"well":[85],"slight":[89],"improvement":[90],"in":[91,102,106],"clean":[92],"conditions,":[93],"these":[94],"yield":[98],"significant":[100],"increase":[101],"recognition":[104],"performance":[105],"various":[107],"noise":[108],"conditions":[109],"when":[110],"compared":[111],"directly":[112],"to":[113],"standard":[115],"temporal":[116],"derivative":[117],"RASTA-PLP":[120]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
