{"id":"https://openalex.org/W1582729625","doi":"https://doi.org/10.1109/icce-tw.2015.7216925","title":"Magnitude replacement of real and imaginary modulation spectrum of acoustic spectrograms for noise-robust speech recognition","display_name":"Magnitude replacement of real and imaginary modulation spectrum of acoustic spectrograms for noise-robust speech recognition","publication_year":2015,"publication_date":"2015-06-01","ids":{"openalex":"https://openalex.org/W1582729625","doi":"https://doi.org/10.1109/icce-tw.2015.7216925","mag":"1582729625"},"language":"en","primary_location":{"id":"doi:10.1109/icce-tw.2015.7216925","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce-tw.2015.7216925","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Consumer Electronics - Taiwan","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/A5075362783","display_name":"Hsin-Ju Hsieh","orcid":null},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Hsin-Ju Hsieh","raw_affiliation_strings":["Department of Electrical Engineering, National Chi Nan University, Taiwan","Department of Electrical Engineering, National Chi Nan University, Taiwan#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Chi Nan University, Taiwan","institution_ids":["https://openalex.org/I193365169"]},{"raw_affiliation_string":"Department of Electrical Engineering, National Chi Nan University, Taiwan#TAB#","institution_ids":["https://openalex.org/I193365169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019048236","display_name":"Jeih-weih Hung","orcid":"https://orcid.org/0000-0001-9366-3070"},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jeih-weih Hung","raw_affiliation_strings":["Department of Electrical Engineering, National Chi Nan University, Taiwan","Department of Electrical Engineering, National Chi Nan University, Taiwan#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Chi Nan University, Taiwan","institution_ids":["https://openalex.org/I193365169"]},{"raw_affiliation_string":"Department of Electrical Engineering, National Chi Nan University, Taiwan#TAB#","institution_ids":["https://openalex.org/I193365169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5075362783"],"corresponding_institution_ids":["https://openalex.org/I193365169"],"apc_list":null,"apc_paid":null,"fwci":0.5743,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6504577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"328","last_page":"329"},"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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/spectrogram","display_name":"Spectrogram","score":0.9591811299324036},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7368168830871582},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6920835971832275},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6852611899375916},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6355664730072021},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.5009841918945312},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4690309762954712},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.462988018989563},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.44526898860931396},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43285316228866577},{"id":"https://openalex.org/keywords/frequency-modulation","display_name":"Frequency modulation","score":0.42459627985954285},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4065372943878174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36490243673324585},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3313485383987427},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.19504383206367493},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11428606510162354},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11022335290908813},{"id":"https://openalex.org/keywords/radio-frequency","display_name":"Radio frequency","score":0.10030403733253479},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07562223076820374}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9591811299324036},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7368168830871582},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6920835971832275},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6852611899375916},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6355664730072021},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.5009841918945312},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4690309762954712},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.462988018989563},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.44526898860931396},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43285316228866577},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.42459627985954285},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4065372943878174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36490243673324585},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3313485383987427},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.19504383206367493},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11428606510162354},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11022335290908813},{"id":"https://openalex.org/C74064498","wikidata":"https://www.wikidata.org/wiki/Q3396184","display_name":"Radio frequency","level":2,"score":0.10030403733253479},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07562223076820374},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icce-tw.2015.7216925","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce-tw.2015.7216925","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Consumer Electronics - Taiwan","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2052667477","https://openalex.org/W2066561607","https://openalex.org/W2069976350","https://openalex.org/W2115515280","https://openalex.org/W2122358934","https://openalex.org/W2151484683","https://openalex.org/W2171000037","https://openalex.org/W4256112632"],"related_works":["https://openalex.org/W1975881626","https://openalex.org/W4252208810","https://openalex.org/W774601707","https://openalex.org/W2042126215","https://openalex.org/W1661822825","https://openalex.org/W3011514165","https://openalex.org/W2188881610","https://openalex.org/W2162374031","https://openalex.org/W3129467116","https://openalex.org/W2066622061"],"abstract_inverted_index":{"In":[0],"this":[1,69],"paper,":[2],"a":[3],"novel":[4,70],"method":[5,52,71],"is":[6],"proposed":[7],"to":[8,29],"enhance":[9],"the":[10,19,23,37,42,50,56,73],"complex-valued":[11],"acoustic":[12],"spectrograms":[13],"of":[14,22,75],"speech":[15,78],"signals":[16],"via":[17],"replacing":[18],"magnitude":[20],"part":[21],"corresponding":[24],"modulation":[25],"spectrum":[26],"in":[27,77],"order":[28],"create":[30],"noise-robust":[31,62],"feature":[32],"representation":[33],"for":[34],"recognition.":[35],"All":[36],"evaluation":[38],"experiments":[39],"implemented":[40],"on":[41],"Aurora-2":[43],"digit":[44],"database":[45],"and":[46,59],"task":[47],"show":[48],"that":[49,68],"presented":[51],"performs":[53],"better":[54],"than":[55],"baseline":[57],"MFCC":[58],"several":[60],"well-known":[61],"techniques.":[63],"These":[64],"results":[65],"apparently":[66],"reveal":[67],"alleviates":[72],"effect":[74],"noise":[76],"features":[79],"significantly.":[80]},"counts_by_year":[{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}