{"id":"https://openalex.org/W2655992787","doi":"https://doi.org/10.1109/icassp.2017.7953147","title":"Harmonic feature fusion for robust neural network-based acoustic modeling","display_name":"Harmonic feature fusion for robust neural network-based acoustic modeling","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2655992787","doi":"https://doi.org/10.1109/icassp.2017.7953147","mag":"2655992787"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953147","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 Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5033500018","display_name":"Osamu Ichikawa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Osamu Ichikawa","raw_affiliation_strings":["Watson Multimodal, IBM, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Watson Multimodal, IBM, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037089480","display_name":"Takashi Fukuda","orcid":"https://orcid.org/0000-0001-9599-6274"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takashi Fukuda","raw_affiliation_strings":["Watson Multimodal, IBM, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Watson Multimodal, IBM, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102336136","display_name":"Masayuki Suzuki","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masayuki Suzuki","raw_affiliation_strings":["Watson Multimodal, IBM, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Watson Multimodal, IBM, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021294422","display_name":"Gakuto Kurata","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gakuto Kurata","raw_affiliation_strings":["Watson Multimodal, IBM, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Watson Multimodal, IBM, Tokyo, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["Watson Multimodal, IBM, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Watson Multimodal, IBM, Yorktown Heights, NY, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5195","last_page":"5199"},"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":0.9997000098228455,"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":0.9995999932289124,"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":0.7706839442253113},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6509317755699158},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.604150116443634},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5547385215759277},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5527766346931458},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5139474272727966},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48479169607162476},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.4714715778827667},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4586738049983978},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4272296130657196},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4262887239456177},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.42557424306869507},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.22697284817695618},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.21217209100723267},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.119498610496521}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7706839442253113},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6509317755699158},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.604150116443634},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5547385215759277},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5527766346931458},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5139474272727966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48479169607162476},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.4714715778827667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4586738049983978},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4272296130657196},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4262887239456177},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42557424306869507},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.22697284817695618},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.21217209100723267},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.119498610496521},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/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/icassp.2017.7953147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953147","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 Acoustics, Speech and Signal Processing (ICASSP)","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":31,"referenced_works":["https://openalex.org/W1542280630","https://openalex.org/W1969851134","https://openalex.org/W1989314204","https://openalex.org/W2017608047","https://openalex.org/W2062164080","https://openalex.org/W2106700313","https://openalex.org/W2112739286","https://openalex.org/W2141102245","https://openalex.org/W2147768505","https://openalex.org/W2149457403","https://openalex.org/W2154833897","https://openalex.org/W2172097686","https://openalex.org/W2237224976","https://openalex.org/W2289912446","https://openalex.org/W2292733088","https://openalex.org/W2296167893","https://openalex.org/W2398826216","https://openalex.org/W2408093180","https://openalex.org/W2475988411","https://openalex.org/W2508048623","https://openalex.org/W2963175699","https://openalex.org/W2963920996","https://openalex.org/W4293764390","https://openalex.org/W4297665160","https://openalex.org/W6629052376","https://openalex.org/W6678409544","https://openalex.org/W6682034417","https://openalex.org/W6682210715","https://openalex.org/W6690441418","https://openalex.org/W6697199058","https://openalex.org/W6712560600"],"related_works":["https://openalex.org/W151018310","https://openalex.org/W3081187864","https://openalex.org/W4380605396","https://openalex.org/W3133352777","https://openalex.org/W2008737763","https://openalex.org/W2584084702","https://openalex.org/W2784059283","https://openalex.org/W4319779560","https://openalex.org/W3012383599","https://openalex.org/W4385611764"],"abstract_inverted_index":{"Acoustic":[0],"modeling":[1,72],"with":[2,99,109,123,152],"deep":[3],"learning":[4],"has":[5],"drastically":[6],"improved":[7],"the":[8,16,20,29,53,59,78,100,105,120,139,153,158],"performance":[9],"of":[10,19,126],"automatic":[11],"speech":[12],"recognition":[13],"(ASR)":[14],"where":[15],"main":[17],"stream":[18],"acoustic":[21,71,102,121],"feature":[22],"is":[23,88,107],"still":[24,37],"log-Mel":[25,30],"filtered":[26,31],"one.":[27],"While":[28],"features":[32,68,96,122],"lose":[33],"harmonic-structure":[34],"information,":[35],"they":[36],"include":[38],"useful":[39],"information":[40,51],"for":[41],"ASR.":[42],"Several":[43],"attempts":[44],"have":[45,81],"been":[46],"made":[47],"to":[48,57,73],"integrate":[49],"higher-resolution":[50],"into":[52,70],"network.":[54],"In":[55],"order":[56],"improve":[58],"ASR":[60],"accuracy":[61,160],"in":[62,77,91,143,149,161],"noisy":[63,92,113],"conditions,":[64],"we":[65],"propose":[66],"new":[67,95],"integrated":[69],"represent":[74],"which":[75,130],"parts":[76,131],"time-frequency":[79],"domain":[80],"a":[82,124],"distinct":[83],"harmonic":[84],"structure,":[85],"since":[86],"it":[87,118],"partially":[89],"observed":[90],"environments.":[93],"The":[94],"are":[97,132],"combined":[98],"standard":[101],"features,":[103],"and":[104],"network":[106],"trained":[108],"them":[110],"using":[111],"various":[112],"data.":[114],"Through":[115],"these":[116],"operations,":[117],"learns":[119],"kind":[125],"quality":[127],"tag":[128],"describing":[129],"clean":[133,162],"or":[134],"degraded.":[135],"Our":[136],"model":[137],"reduced":[138],"word":[140],"error":[141],"rate":[142],"an":[144],"Aurora-4":[145],"task":[146],"by":[147],"10.3%":[148],"DNN":[150],"compared":[151],"strong":[154],"baseline":[155],"while":[156],"retaining":[157],"high":[159],"test":[163],"cases.":[164]},"counts_by_year":[{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}