{"id":"https://openalex.org/W2739959771","doi":"https://doi.org/10.1109/sped.2017.7990430","title":"Multi-resolution spectral input for convolutional neural network-based speech recognition","display_name":"Multi-resolution spectral input for convolutional neural network-based speech recognition","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2739959771","doi":"https://doi.org/10.1109/sped.2017.7990430","mag":"2739959771"},"language":"en","primary_location":{"id":"doi:10.1109/sped.2017.7990430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped.2017.7990430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","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/A5020608163","display_name":"L\u00e1szl\u00f3 T\u00f3th","orcid":"https://orcid.org/0000-0003-0161-1375"},"institutions":[{"id":"https://openalex.org/I4210152167","display_name":"MTA-SZTE Research Group on Artificial Intelligence","ror":"https://ror.org/0507fk326","country_code":"HU","type":"facility","lineage":["https://openalex.org/I227486990","https://openalex.org/I4210152167","https://openalex.org/I7597260"]},{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"funder","lineage":["https://openalex.org/I7597260"]},{"id":"https://openalex.org/I227486990","display_name":"University of Szeged","ror":"https://ror.org/01pnej532","country_code":"HU","type":"education","lineage":["https://openalex.org/I227486990"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Laszlo Toth","raw_affiliation_strings":["MTA-SZTE Research Group on Artificial Intelligence Hungarian Academy of Sciences and University of Szeged"],"affiliations":[{"raw_affiliation_string":"MTA-SZTE Research Group on Artificial Intelligence Hungarian Academy of Sciences and University of Szeged","institution_ids":["https://openalex.org/I4210152167","https://openalex.org/I227486990","https://openalex.org/I7597260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5020608163"],"corresponding_institution_ids":["https://openalex.org/I227486990","https://openalex.org/I4210152167","https://openalex.org/I7597260"],"apc_list":null,"apc_paid":null,"fwci":0.7801,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79206369,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"abs 1207 580","issue":null,"first_page":"1","last_page":"6"},"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/T11309","display_name":"Music and Audio Processing","score":0.9976000189781189,"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":0.8148097991943359},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.8000329732894897},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6606837511062622},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5692936182022095},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5654569268226624},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5450206398963928},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5373092889785767},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5161029100418091},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5037209391593933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5018019676208496},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.43737146258354187},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4172230362892151},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.19550150632858276},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09184408187866211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8148097991943359},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.8000329732894897},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6606837511062622},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5692936182022095},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5654569268226624},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5450206398963928},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5373092889785767},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5161029100418091},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5037209391593933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5018019676208496},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.43737146258354187},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4172230362892151},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.19550150632858276},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09184408187866211},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sped.2017.7990430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped.2017.7990430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W136469843","https://openalex.org/W811578723","https://openalex.org/W1569189596","https://openalex.org/W1904365287","https://openalex.org/W1968419113","https://openalex.org/W1987841215","https://openalex.org/W1993882792","https://openalex.org/W2022011789","https://openalex.org/W2035424729","https://openalex.org/W2062227835","https://openalex.org/W2063689849","https://openalex.org/W2112739286","https://openalex.org/W2132522985","https://openalex.org/W2143612262","https://openalex.org/W2154833897","https://openalex.org/W2155273149","https://openalex.org/W2184481212","https://openalex.org/W2188183693","https://openalex.org/W2403922683","https://openalex.org/W2404068704","https://openalex.org/W2962719052","https://openalex.org/W6640036494","https://openalex.org/W6679518233","https://openalex.org/W6686550187","https://openalex.org/W6713454745","https://openalex.org/W6713646301"],"related_works":["https://openalex.org/W1669577408","https://openalex.org/W2994894110","https://openalex.org/W4377862891","https://openalex.org/W2005708641","https://openalex.org/W2050397613","https://openalex.org/W2080458333","https://openalex.org/W1995562189","https://openalex.org/W172689163","https://openalex.org/W2145230572","https://openalex.org/W1507177964"],"abstract_inverted_index":{"The":[0],"convolutional":[1],"deep":[2],"neural":[3],"network":[4,59,94],"component":[5],"applied":[6],"frequently":[7],"in":[8],"current":[9],"speech":[10],"recognizers":[11],"is":[12,141],"trained":[13],"on":[14,134,148],"a":[15,48,75,96,113,128],"context":[16,98],"of":[17,32,39,64,92,99,106,118,132],"consecutive":[18],"spectral":[19,40],"feature":[20],"vectors.":[21],"Here,":[22],"we":[23,26,86,110],"investigate":[24],"whether":[25],"can":[27],"extend":[28,89],"the":[29,37,43,54,58,61,65,69,90,104,122,135,144],"time":[30,45,97],"span":[31],"this":[33,84,149],"input":[34,91,107],"and":[35,109],"reduce":[36],"number":[38,105],"features":[41],"at":[42],"same":[44],"by":[46],"using":[47,68],"multi-resolution":[49,56],"spectrum":[50],"as":[51],"input.":[52],"In":[53],"proposed":[55],"scheme,":[57],"processes":[60],"nearby":[62],"neighbors":[63],"actual":[66],"frame":[67],"standard":[70],"resolution,":[71],"while":[72],"it":[73],"applies":[74],"gradually":[76],"coarser":[77],"resolution":[78],"for":[79],"more":[80],"distant":[81],"frames.":[82],"Using":[83],"solution,":[85],"managed":[87],"to":[88,95,121],"our":[93],"45":[100],"frames":[101],"without":[102],"increasing":[103],"features,":[108],"also":[111],"achieved":[112],"relative":[114],"error":[115,130],"rate":[116,131],"reduction":[117],"3-4%":[119],"compared":[120],"conventional":[123],"high-resolution":[124],"representation.":[125],"We":[126],"report":[127],"phone":[129],"17.0%":[133],"TIMIT":[136],"core":[137],"test":[138],"set,":[139],"which":[140],"competitive":[142],"with":[143],"best":[145],"scores":[146],"published":[147],"data":[150],"set.":[151]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}