{"id":"https://openalex.org/W2118858754","doi":"https://doi.org/10.21437/interspeech.2008-445","title":"On the combination of auditory and modulation frequency channels for ASR applications","display_name":"On the combination of auditory and modulation frequency channels for ASR applications","publication_year":2008,"publication_date":"2008-09-22","ids":{"openalex":"https://openalex.org/W2118858754","doi":"https://doi.org/10.21437/interspeech.2008-445","mag":"2118858754"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2008-445","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://publications.idiap.ch/downloads/papers/2008/valente-Interspeech2-2008.pdf","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]},{"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/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":"Hynek Hermansky","raw_affiliation_strings":["Idiap Research Institute, Martigny-Combe, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny-Combe, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2242","last_page":"2245"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9986000061035156,"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":0.7368983030319214},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7032325267791748},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.6204013228416443},{"id":"https://openalex.org/keywords/frequency-modulation","display_name":"Frequency modulation","score":0.5907220244407654},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4988734722137451},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44812601804733276},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3983040452003479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39462804794311523},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.25739723443984985},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2204892635345459},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14120230078697205},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0934019386768341}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7368983030319214},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7032325267791748},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.6204013228416443},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.5907220244407654},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4988734722137451},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44812601804733276},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3983040452003479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39462804794311523},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.25739723443984985},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2204892635345459},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14120230078697205},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0934019386768341}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2008-445","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.tind.io:146325","is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/valente:rr08-12","pdf_url":"http://publications.idiap.ch/downloads/papers/2008/valente-Interspeech2-2008.pdf","source":{"id":"https://openalex.org/S4306400488","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":false,"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":"http://infoscience.epfl.ch/record/146325","raw_type":"Text"},{"id":"pmh:oai:infoscience.tind.io:146500","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146500","pdf_url":"http://publications.idiap.ch/downloads/reports/2008/valente-idiap-rr-08-12.pdf","source":{"id":"https://openalex.org/S4306400488","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":false,"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":"http://infoscience.epfl.ch/record/146500","raw_type":"Text"},{"id":"pmh:oai:infoscience.epfl.ch:146325","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146325","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:146325","is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/valente:rr08-12","pdf_url":"http://publications.idiap.ch/downloads/papers/2008/valente-Interspeech2-2008.pdf","source":{"id":"https://openalex.org/S4306400488","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":false,"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":"http://infoscience.epfl.ch/record/146325","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3190074090","display_name":null,"funder_award_id":"HR0011-06-C-0023","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2118858754.pdf"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W130921173","https://openalex.org/W1493755359","https://openalex.org/W1920478749","https://openalex.org/W1922557984","https://openalex.org/W1992272902","https://openalex.org/W2046331056","https://openalex.org/W2052922189","https://openalex.org/W2101596234","https://openalex.org/W2102512139","https://openalex.org/W2135217244","https://openalex.org/W2141499240","https://openalex.org/W2158010000","https://openalex.org/W2468573742","https://openalex.org/W4243233711","https://openalex.org/W4299602298","https://openalex.org/W4302613066"],"related_works":["https://openalex.org/W4387474130","https://openalex.org/W2004723848","https://openalex.org/W2086788376","https://openalex.org/W2093157008","https://openalex.org/W1518527075","https://openalex.org/W2162174235","https://openalex.org/W2143773860","https://openalex.org/W2068642629","https://openalex.org/W2012415775","https://openalex.org/W2054254129"],"abstract_inverted_index":{"This":[0,100],"paper":[1],"investigates":[2],"the":[3,14,102,112],"combination":[4,31,57],"of":[5,32,38,58,64,97],"evidence":[6,87],"coming":[7,88],"from":[8,89],"different":[9,18,36,62,90],"frequency":[10,92],"channels":[11],"obtained":[12],"filtering":[13],"speech":[15],"signal":[16],"at":[17],"auditory":[19],"and":[20],"modulation":[21],"frequencies.":[22],"In":[23,51],"our":[24],"previous":[25,98],"work":[26,53],"\\\\cite{icassp2008},":[27],"we":[28,54,77],"showed":[29],"that":[30,56,94],"classifiers":[33,59],"trained":[34,60],"on":[35,61,82],"ranges":[37,63],"{\\\\it":[39,65],"modulation}":[40],"frequencies":[41,67],"is":[42,68],"more":[43,69],"effective":[44,70],"if":[45,71],"performed":[46,72],"in":[47,73,116],"sequential":[48],"(hierarchical)":[49],"fashion.":[50,75],"this":[52],"verify":[55],"auditory}":[66],"parallel":[74],"Furthermore":[76],"propose":[78],"an":[79],"architecture":[80],"based":[81],"neural":[83],"networks":[84],"for":[85],"combining":[86],"auditory-modulation":[91],"sub-bands":[93],"takes":[95],"advantages":[96],"findings.":[99],"reduces":[101],"final":[103],"WER":[104],"by":[105],"6.2\\\\%":[106],"(from":[107],"45.8\\\\%":[108],"to":[109],"39.6\\\\%)":[110],"w.r.t":[111],"single":[113],"classifier":[114],"approach":[115],"a":[117],"LVCSR":[118],"task.":[119]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
