{"id":"https://openalex.org/W2753802668","doi":"https://doi.org/10.1109/icme.2017.8019385","title":"Multi-scale feature based convolutional neural networks for large vocabulary speech recognition","display_name":"Multi-scale feature based convolutional neural networks for large vocabulary speech recognition","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2753802668","doi":"https://doi.org/10.1109/icme.2017.8019385","mag":"2753802668"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2017.8019385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2017.8019385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Multimedia and Expo (ICME)","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/A5102014712","display_name":"Tong Fu","orcid":"https://orcid.org/0000-0001-7669-6903"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tong Fu","raw_affiliation_strings":["Speech and Hearing Research Center, Peking University, Beijing"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Center, Peking University, Beijing","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084685506","display_name":"Xihong Wu","orcid":"https://orcid.org/0009-0004-5236-7469"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihong Wu","raw_affiliation_strings":["Speech and Hearing Research Center, Peking University, Beijing"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Center, Peking University, Beijing","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102014712"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.195,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62257393,"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":"1093","last_page":"1098"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9977999925613403,"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":0.9973999857902527,"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":0.8107882738113403},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7633330821990967},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6537745594978333},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6140048503875732},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5788332223892212},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5329568982124329},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5154793858528137},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49697187542915344},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.493533730506897},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.491397500038147},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48111122846603394},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4709887206554413},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4442909061908722},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.425396591424942},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4202905297279358},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.41242337226867676},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.343256413936615},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.20702365040779114},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08268174529075623},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0740894079208374}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8107882738113403},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7633330821990967},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6537745594978333},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6140048503875732},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5788332223892212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5329568982124329},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5154793858528137},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49697187542915344},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.493533730506897},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.491397500038147},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48111122846603394},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4709887206554413},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4442909061908722},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.425396591424942},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4202905297279358},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.41242337226867676},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.343256413936615},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.20702365040779114},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08268174529075623},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0740894079208374},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2017.8019385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2017.8019385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W162588823","https://openalex.org/W217970951","https://openalex.org/W1538131130","https://openalex.org/W1600744878","https://openalex.org/W1688610710","https://openalex.org/W1815076433","https://openalex.org/W1907282891","https://openalex.org/W1922655562","https://openalex.org/W2057653135","https://openalex.org/W2077804127","https://openalex.org/W2102113734","https://openalex.org/W2116456623","https://openalex.org/W2147768505","https://openalex.org/W2152624700","https://openalex.org/W2188736355","https://openalex.org/W2198724430","https://openalex.org/W2293634267","https://openalex.org/W2394932179","https://openalex.org/W2401869809","https://openalex.org/W2408093180","https://openalex.org/W6608710415","https://openalex.org/W6635768407","https://openalex.org/W6640090968","https://openalex.org/W6675365184","https://openalex.org/W6682712192","https://openalex.org/W6687812937","https://openalex.org/W6713197546"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W2766680336","https://openalex.org/W1980297060","https://openalex.org/W3134920593","https://openalex.org/W2133320490","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W4289830142","https://openalex.org/W1497065097","https://openalex.org/W2373675101"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"has":[2],"brought":[3],"a":[4,66,93,101],"breakthrough":[5],"to":[6,96,106],"the":[7,23,35,40,58,62,69,73,98,122,138],"performance":[8,25,145],"of":[9,61,72,132],"speech":[10,13,28,108],"recognition.":[11],"The":[12],"recognition":[14,29],"systems":[15,32],"based":[16,46,56,83],"on":[17,26,47,57,84,115],"deep":[18],"neural":[19],"networks":[20],"have":[21],"obtained":[22],"state-of-the-art":[24],"various":[27,130],"tasks.":[30],"These":[31],"almost":[33],"utilize":[34],"Mel-frequency":[36],"cepstral":[37],"coefficients":[38],"or":[39],"Mel-scale":[41],"log-filterbank":[42],"coefficients,":[43],"which":[44],"are":[45,54,113],"short-time":[48,85],"Fourier":[49,86],"transform.":[50,87],"Although":[51],"these":[52],"features":[53,125,128],"designed":[55],"auditory":[59],"characteristics":[60],"human,":[63],"it":[64],"is":[65],"problem":[67],"that":[68,104,137],"inherent":[70],"tradeoff":[71,99],"temporal":[74],"and":[75,100,117,126],"frequency":[76],"resolution":[77],"still":[78],"exists":[79],"in":[80],"spectral":[81],"representations":[82],"In":[88],"this":[89],"paper,":[90],"we":[91],"propose":[92],"multi-scale":[94,124],"method":[95],"mitigate":[97],"model":[102,140],"architecture":[103,141],"enables":[105],"analyze":[107],"at":[109,129],"multiple":[110],"scale.":[111],"Experiments":[112],"conducted":[114],"TIMIT":[116],"HKUST":[118],"corpus.":[119],"We":[120],"compare":[121],"proposed":[123,139],"traditional":[127],"number":[131],"configurations.":[133],"Experimental":[134],"results":[135],"show":[136],"can":[142],"obtain":[143],"significant":[144],"improvement.":[146]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}