{"id":"https://openalex.org/W2401264858","doi":"https://doi.org/10.21437/interspeech.2015-421","title":"DNN derived filters for processing of modulation spectrum of speech","display_name":"DNN derived filters for processing of modulation spectrum of speech","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2401264858","doi":"https://doi.org/10.21437/interspeech.2015-421","mag":"2401264858"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-421","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034181217","display_name":"Jan Pe\u0161\u00e1n","orcid":"https://orcid.org/0000-0002-9655-1143"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Pe\u0161\u00e1n","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luk\u00e1\u0161 Burget","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042260050","display_name":"Hynek He\u0159mansk\u00fd","orcid":"https://orcid.org/0000-0001-8032-4811"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hynek Hermansky","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5045351360","display_name":"Karel Vesel\u00fd","orcid":"https://orcid.org/0000-0002-3568-7493"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karel Vesel\u00fd","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8903,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84458312,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1908","last_page":"1911"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.766374945640564},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7086676359176636},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5850307941436768},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.5637195110321045},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.500767707824707},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.46945399045944214},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.4373440146446228},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4262399673461914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40197136998176575},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.37886568903923035},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3610571622848511},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.21983104944229126},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.20179066061973572},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.0940999686717987},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0810820460319519},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08004620671272278}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.766374945640564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7086676359176636},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5850307941436768},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.5637195110321045},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.500767707824707},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.46945399045944214},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4373440146446228},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4262399673461914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40197136998176575},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.37886568903923035},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3610571622848511},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.21983104944229126},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.20179066061973572},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0940999686717987},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0810820460319519},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08004620671272278},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-421","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W22365","https://openalex.org/W9692546","https://openalex.org/W154677192","https://openalex.org/W162588823","https://openalex.org/W1970890968","https://openalex.org/W1975366770","https://openalex.org/W2038728370","https://openalex.org/W2069999512","https://openalex.org/W2101596234","https://openalex.org/W2137075158","https://openalex.org/W2148154194","https://openalex.org/W2395240357","https://openalex.org/W2914484425"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2131486661","https://openalex.org/W2114026179","https://openalex.org/W2089240210","https://openalex.org/W564807179","https://openalex.org/W2389042244","https://openalex.org/W2108641942"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2],"novel":[3],"approach":[4],"to":[5],"design":[6],"modulation":[7,30,86],"frequency":[8,31],"filters":[9,27,32,53],"for":[10,73,77],"the":[11],"first":[12],"stage":[13],"processing":[14,67,90],"of":[15,19,61,64,75],"critical":[16],"band":[17],"spectrum":[18],"speech":[20,38,76],"using":[21],"deep":[22,81],"neural":[23,82],"network":[24],"(DNN).":[25],"These":[26],"replace":[28],"conventional":[29],"currently":[33],"used":[34],"in":[35,47],"state-of-the-art":[36],"BUT":[37],"recognition":[39,49],"system":[40],"and":[41,68],"yield":[42],"about":[43],"10%":[44],"relative":[45],"improvement":[46],"phoneme":[48],"accuracy.":[50],"The":[51],"resulting":[52],"are":[54],"consistent":[55],"with":[56],"some":[57],"known":[58],"temporal":[59],"properties":[60],"higher":[62],"levels":[63],"mammalian":[65,88],"auditory":[66,89],"suggest":[69],"more":[70],"efficient":[71],"scheme":[72],"pre-processing":[74],"ASR.":[78],"Index":[79],"Terms:":[80],"network,":[83],"convolutive":[84],"layer,":[85],"filters,":[87]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}