{"id":"https://openalex.org/W4390120023","doi":"https://doi.org/10.1109/lsp.2023.3346280","title":"Automatic Audio Feature Extraction for Keyword Spotting","display_name":"Automatic Audio Feature Extraction for Keyword Spotting","publication_year":2023,"publication_date":"2023-12-22","ids":{"openalex":"https://openalex.org/W4390120023","doi":"https://doi.org/10.1109/lsp.2023.3346280"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2023.3346280","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3346280","pdf_url":"https://ieeexplore.ieee.org/ielx7/97/4358004/10371787.pdf","source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/97/4358004/10371787.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088875863","display_name":"Paola Vitolo","orcid":"https://orcid.org/0000-0001-6703-3999"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paola Vitolo","raw_affiliation_strings":["Department of Industrial Engineering, University of Salerno, Fisciano, Salerno, Italy"],"raw_orcid":"https://orcid.org/0000-0001-6703-3999","affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering, University of Salerno, Fisciano, Salerno, Italy","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029809556","display_name":"Rosalba Liguori","orcid":"https://orcid.org/0000-0002-0093-1169"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Rosalba Liguori","raw_affiliation_strings":["Department of Industrial Engineering, University of Salerno, Fisciano, Salerno, Italy"],"raw_orcid":"https://orcid.org/0000-0002-0093-1169","affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering, University of Salerno, Fisciano, Salerno, Italy","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026535044","display_name":"Luigi Di Benedetto","orcid":"https://orcid.org/0000-0001-5588-0621"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luigi Di Benedetto","raw_affiliation_strings":["Department of Industrial Engineering, University of Salerno, Fisciano, Salerno, Italy"],"raw_orcid":"https://orcid.org/0000-0001-5588-0621","affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering, University of Salerno, Fisciano, Salerno, Italy","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044628138","display_name":"Alfredo Rubino","orcid":"https://orcid.org/0000-0002-5690-9040"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alfredo Rubino","raw_affiliation_strings":["Department of Industrial Engineering, University of Salerno, Fisciano, Salerno, Italy"],"raw_orcid":"https://orcid.org/0000-0002-5690-9040","affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering, University of Salerno, Fisciano, Salerno, Italy","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030070417","display_name":"Gian Domenico Licciardo","orcid":"https://orcid.org/0000-0002-1913-4928"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gian Domenico Licciardo","raw_affiliation_strings":["Department of Industrial Engineering, University of Salerno, Fisciano, Salerno, Italy"],"raw_orcid":"https://orcid.org/0000-0002-1913-4928","affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering, University of Salerno, Fisciano, Salerno, Italy","institution_ids":["https://openalex.org/I131729948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I131729948"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":{"value":2645,"currency":"USD","value_usd":2645},"fwci":1.2925,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84168131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"31","issue":null,"first_page":"161","last_page":"165"},"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/T11309","display_name":"Music 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/T10860","display_name":"Speech 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/keyword-spotting","display_name":"Keyword spotting","score":0.9282907843589783},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8372886776924133},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6822429895401001},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6121026873588562},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.6115926504135132},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5732876658439636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5603386163711548},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5473589301109314},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5398944616317749},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5040375590324402},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.49798011779785156},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.47412919998168945},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.45991411805152893},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4586816132068634},{"id":"https://openalex.org/keywords/computational-resource","display_name":"Computational resource","score":0.43700164556503296},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3396907150745392},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3000897765159607},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09844979643821716}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9282907843589783},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8372886776924133},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6822429895401001},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6121026873588562},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.6115926504135132},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5732876658439636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5603386163711548},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5473589301109314},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5398944616317749},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5040375590324402},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.49798011779785156},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.47412919998168945},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.45991411805152893},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4586816132068634},{"id":"https://openalex.org/C127964446","wikidata":"https://www.wikidata.org/wiki/Q1092142","display_name":"Computational resource","level":3,"score":0.43700164556503296},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3396907150745392},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3000897765159607},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09844979643821716},{"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/lsp.2023.3346280","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3346280","pdf_url":"https://ieeexplore.ieee.org/ielx7/97/4358004/10371787.pdf","source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/lsp.2023.3346280","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3346280","pdf_url":"https://ieeexplore.ieee.org/ielx7/97/4358004/10371787.pdf","source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390120023.pdf","grobid_xml":"https://content.openalex.org/works/W4390120023.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W2271840356","https://openalex.org/W2755354578","https://openalex.org/W2769912137","https://openalex.org/W2797583228","https://openalex.org/W2942231644","https://openalex.org/W2972869267","https://openalex.org/W3019215432","https://openalex.org/W3047171309","https://openalex.org/W3092256386","https://openalex.org/W3120595804","https://openalex.org/W3138037053","https://openalex.org/W3168997536","https://openalex.org/W3201897989","https://openalex.org/W4205550152","https://openalex.org/W4206567542","https://openalex.org/W4213445103","https://openalex.org/W4285292186","https://openalex.org/W4293070540","https://openalex.org/W4295855486","https://openalex.org/W4308521107","https://openalex.org/W4312977143","https://openalex.org/W4313178214","https://openalex.org/W4319431332","https://openalex.org/W4322485494","https://openalex.org/W4323644307","https://openalex.org/W4387493896","https://openalex.org/W6673335734","https://openalex.org/W6694517276","https://openalex.org/W6746451879","https://openalex.org/W6750665317","https://openalex.org/W6852853452"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W3119978414","https://openalex.org/W2114097550","https://openalex.org/W2545741539","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W1969408022","https://openalex.org/W4390120023"],"abstract_inverted_index":{"The":[0],"accuracy":[1,72,137],"and":[2,70,112,186],"computational":[3,67,184],"complexity":[4,68,185],"of":[5,16,49,61,74,83,90,106,115,166,171,176],"keyword":[6],"spotting":[7],"(KWS)":[8],"systems":[9,78,197],"are":[10,53],"heavily":[11],"influenced":[12],"by":[13,34],"the":[14,45,50,55,59,62,75,81,84,88,97,113,119,128,147,157,163,177],"choice":[15],"audio":[17,29,63,130],"features":[18],"in":[19,32,44,54,104,109,180,183,198],"speech":[20,122],"signals.":[21],"This":[22],"paper":[23],"introduces":[24],"a":[25,36,181],"novel":[26],"approach":[27,52],"for":[28,193],"feature":[30,131],"extraction":[31,60],"KWS":[33,77,196],"leveraging":[35],"convolutional":[37],"autoencoder,":[38],"which":[39,189],"has":[40],"not":[41],"been":[42],"explored":[43],"existing":[46],"literature.":[47],"Strengths":[48],"proposed":[51,129],"ability":[56],"to":[57,144,153,160],"automate":[58],"features,":[64],"keep":[65],"its":[66],"low,":[69],"allow":[71],"values":[73],"overall":[76],"comparable":[79],"with":[80,96,195],"state":[82],"art.":[85],"To":[86],"evaluate":[87],"effectiveness":[89],"our":[91],"proposal,":[92],"we":[93],"compared":[94],"it":[95,191],"widely-used":[98],"Mel":[99],"Frequency":[100],"Cepstrum":[101],"(MFC)":[102],"method":[103],"terms":[105],"classification":[107,136],"metrics":[108],"noisy":[110],"conditions":[111],"number":[114,165],"required":[116,164],"operators,":[117],"using":[118],"public":[120],"Google":[121],"command":[123],"dataset.":[124],"Results":[125],"demonstrate":[126],"that":[127,175],"extractor":[132],"achieves":[133],"an":[134],"average":[135],"on":[138],"12":[139],"classes":[140],"ranging":[141],"from":[142,151],"81.84%":[143],"90.36%":[145],"when":[146],"signal-tonoise":[148],"ratio":[149],"spans":[150],"0":[152],"40":[154],"dB,":[155],"outperforming":[156],"MFC":[158],"up":[159],"5.2%.":[161],"Furthermore,":[162],"operations":[167],"is":[168],"one":[169],"order":[170],"magnitude":[172],"lower":[173],"than":[174],"MFC,":[178],"resulting":[179],"reduction":[182],"processing":[187],"time,":[188],"makes":[190],"well-suited":[192],"integration":[194],"resource-constrained":[199],"edge":[200],"devices":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}