{"id":"https://openalex.org/W2921899015","doi":"https://doi.org/10.23919/apsipa.2018.8659610","title":"Applying Complex-Valued Neural Networks to Acoustic Modeling for Speech Recognition","display_name":"Applying Complex-Valued Neural Networks to Acoustic Modeling for Speech Recognition","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2921899015","doi":"https://doi.org/10.23919/apsipa.2018.8659610","mag":"2921899015"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659610","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659610","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5084264065","display_name":"Daichi Hayakawa","orcid":"https://orcid.org/0000-0002-2783-5943"},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Daichi Hayakawa","raw_affiliation_strings":["Corporate Research & Development Center, Toshiba Corporation, Kawasaki, Japan"],"affiliations":[{"raw_affiliation_string":"Corporate Research & Development Center, Toshiba Corporation, Kawasaki, Japan","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064866374","display_name":"Takashi Masuko","orcid":"https://orcid.org/0000-0002-2410-2007"},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Masuko","raw_affiliation_strings":["Corporate Research & Development Center, Toshiba Corporation, Kawasaki, Japan"],"affiliations":[{"raw_affiliation_string":"Corporate Research & Development Center, Toshiba Corporation, Kawasaki, Japan","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113822996","display_name":"Hiroshi Fujimura","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Fujimura","raw_affiliation_strings":["Corporate Research & Development Center, Toshiba Corporation, Kawasaki, Japan"],"affiliations":[{"raw_affiliation_string":"Corporate Research & Development Center, Toshiba Corporation, Kawasaki, Japan","institution_ids":["https://openalex.org/I1292669757"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084264065"],"corresponding_institution_ids":["https://openalex.org/I1292669757"],"apc_list":null,"apc_paid":null,"fwci":0.1629,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.62180704,"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":"1725","last_page":"1731"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9988999962806702,"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/T10320","display_name":"Neural Networks and Applications","score":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7522600889205933},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7287916541099548},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6250077486038208},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5622457265853882},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.49418261647224426},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.45783355832099915},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.41314923763275146},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.4106602668762207},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3731614947319031},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3668874204158783},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.09427082538604736}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7522600889205933},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7287916541099548},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6250077486038208},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5622457265853882},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.49418261647224426},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.45783355832099915},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.41314923763275146},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4106602668762207},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3731614947319031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3668874204158783},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.09427082538604736},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659610","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659610","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":27,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1836465849","https://openalex.org/W2024490156","https://openalex.org/W2024897398","https://openalex.org/W2047515252","https://openalex.org/W2058399474","https://openalex.org/W2069767928","https://openalex.org/W2078951884","https://openalex.org/W2131342762","https://openalex.org/W2134563598","https://openalex.org/W2135858797","https://openalex.org/W2143572124","https://openalex.org/W2150355110","https://openalex.org/W2175402905","https://openalex.org/W2265796482","https://openalex.org/W2289394825","https://openalex.org/W2512499206","https://openalex.org/W2618946976","https://openalex.org/W2788991260","https://openalex.org/W2895966359","https://openalex.org/W2949117887","https://openalex.org/W2951605425","https://openalex.org/W4292692317","https://openalex.org/W6603755213","https://openalex.org/W6631362777","https://openalex.org/W6679429981","https://openalex.org/W6729305679"],"related_works":["https://openalex.org/W564807179","https://openalex.org/W2389042244","https://openalex.org/W2019045084","https://openalex.org/W2004282482","https://openalex.org/W2625914266","https://openalex.org/W2001939451","https://openalex.org/W1523322372","https://openalex.org/W2017201627","https://openalex.org/W2354079427","https://openalex.org/W2025544302"],"abstract_inverted_index":{"Complex-valued":[0],"neural":[1,99],"networks":[2],"(CVNNs)":[3],"are":[4],"well":[5],"suited":[6],"to":[7,36,137],"speech":[8,37],"signal":[9],"processing":[10],"because":[11],"they":[12],"can":[13,114],"naturally":[14],"represent":[15],"amplitude":[16,70],"and":[17,33,48,61,76,93,107,132,139],"phase.":[18],"In":[19],"this":[20],"paper,":[21],"we":[22,40],"explore":[23],"applying":[24],"an":[25,50,84],"acoustic":[26,101,117],"model":[27,102],"with":[28,44,89,96,119],"multiple":[29],"complex-valued":[30,64,79,104,121],"layers":[31,105],"(multiple-CVNN-AM)":[32],"spliced":[34,90],"features":[35,47,92],"recognition.":[38],"First,":[39],"focus":[41],"on":[42],"multiple-CVNN-AM":[43,88,129],"unspliced":[45],"input":[46,91],"investigate":[49,83],"appropriate":[51,85],"architecture":[52,86],"from":[53],"the":[54,57],"viewpoint":[55],"of":[56,63],"activation":[58],"function,":[59],"bias,":[60],"number":[62],"layers.":[65,80,122],"We":[66,81,123],"also":[67],"propose":[68],"batch":[69],"mean":[71],"normalization":[72],"for":[73,87],"more":[74],"quickly":[75],"stably":[77],"training":[78],"then":[82],"compare":[94],"it":[95],"a":[97],"real-valued":[98],"network":[100],"without":[103],"(RVNN-AM)":[106],"complex":[108],"linear":[109],"projection":[110],"(CLP)":[111],"models,":[112],"which":[113],"be":[115],"considered":[116],"models":[118,134],"single":[120],"show":[124],"that":[125],"under":[126],"noise":[127],"conditions,":[128],"outperforms":[130],"RVNN-AM":[131],"CLP":[133],"by":[135],"up":[136],"7.45%":[138],"11.90%,":[140],"respectively.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}