{"id":"https://openalex.org/W3133517635","doi":"https://doi.org/10.1007/978-3-030-70866-5_16","title":"Spectral Analysis for Automatic Speech Recognition and Enhancement","display_name":"Spectral Analysis for Automatic Speech Recognition and Enhancement","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3133517635","doi":"https://doi.org/10.1007/978-3-030-70866-5_16","mag":"3133517635"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-70866-5_16","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-70866-5_16","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/978-3-030-70866-5_16","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057689489","display_name":"Jane Oruh","orcid":"https://orcid.org/0000-0002-7676-7502"},"institutions":[{"id":"https://openalex.org/I95023434","display_name":"University of KwaZulu-Natal","ror":"https://ror.org/04qzfn040","country_code":"ZA","type":"education","lineage":["https://openalex.org/I95023434"]}],"countries":["ZA"],"is_corresponding":true,"raw_author_name":"Jane Oruh","raw_affiliation_strings":["School of Mathematics, Statistics and Computer Science, University of KwaZulu-Natal, Durban, 4000, South Africa"],"affiliations":[{"raw_affiliation_string":"School of Mathematics, Statistics and Computer Science, University of KwaZulu-Natal, Durban, 4000, South Africa","institution_ids":["https://openalex.org/I95023434"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054315649","display_name":"Serestina Viriri","orcid":"https://orcid.org/0000-0002-2850-8645"},"institutions":[{"id":"https://openalex.org/I95023434","display_name":"University of KwaZulu-Natal","ror":"https://ror.org/04qzfn040","country_code":"ZA","type":"education","lineage":["https://openalex.org/I95023434"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Serestina Viriri","raw_affiliation_strings":["School of Mathematics, Statistics and Computer Science, University of KwaZulu-Natal, Durban, 4000, South Africa"],"affiliations":[{"raw_affiliation_string":"School of Mathematics, Statistics and Computer Science, University of KwaZulu-Natal, Durban, 4000, South Africa","institution_ids":["https://openalex.org/I95023434"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5057689489"],"corresponding_institution_ids":["https://openalex.org/I95023434"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":1.8172,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.83124687,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"245","last_page":"254"},"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":0.9994999766349792,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9958999752998352,"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":0.915167510509491},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8178015351295471},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7888169884681702},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.7817234992980957},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5202354192733765},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5144517421722412},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4593714773654938},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45213454961776733},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4476475119590759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43170326948165894},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.41830888390541077},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.30338746309280396},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.27137669920921326},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.12415418028831482},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10843124985694885}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.915167510509491},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8178015351295471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7888169884681702},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.7817234992980957},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5202354192733765},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5144517421722412},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4593714773654938},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45213454961776733},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4476475119590759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43170326948165894},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.41830888390541077},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.30338746309280396},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.27137669920921326},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.12415418028831482},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10843124985694885},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-030-70866-5_16","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-70866-5_16","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-030-70866-5_16","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-70866-5_16","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W7336839","https://openalex.org/W223359644","https://openalex.org/W1494198834","https://openalex.org/W1992833709","https://openalex.org/W2083652170","https://openalex.org/W2101304342","https://openalex.org/W2113318794","https://openalex.org/W2114492997","https://openalex.org/W2134922590","https://openalex.org/W2145830023","https://openalex.org/W2507780144","https://openalex.org/W2564316731","https://openalex.org/W2803433857","https://openalex.org/W2895807593","https://openalex.org/W2998157715","https://openalex.org/W3001172410","https://openalex.org/W3022863654","https://openalex.org/W6640696446","https://openalex.org/W6695659996"],"related_works":["https://openalex.org/W2120540196","https://openalex.org/W3095343173","https://openalex.org/W2381036744","https://openalex.org/W2288135719","https://openalex.org/W2323749021","https://openalex.org/W2533590149","https://openalex.org/W2901989338","https://openalex.org/W82005754","https://openalex.org/W2334448276","https://openalex.org/W4200596008"],"abstract_inverted_index":{"Accurate":[0],"recognition":[1,15,22,52,98],"of":[2,13,19,34,53,74,148],"noisy":[3],"speech":[4,14,21,55,66,97,141,159],"signal":[5,56,117],"is":[6,24,57,93,104,118,135,152],"still":[7],"an":[8,146,156],"obstacle":[9],"for":[10,48,95,108],"wider":[11],"application":[12],"technology.":[16],"The":[17,111],"robustness":[18],"a":[20,40,126],"system":[23],"heavily":[25],"influenced":[26],"by":[27],"the":[28,32,49,54,72,83,105,114,138],"ability":[29],"to":[30,124,154],"handle":[31],"presence":[33],"background":[35],"noise.":[36],"In":[37],"this":[38,70,109],"work,":[39],"Short":[41],"Time":[42],"Fourier":[43],"Transform":[44],"(STFT)":[45],"filtering":[46,61],"technique":[47],"enhancement":[50],"and":[51,99,143],"presented.":[58],"Conventionally,":[59],"STFT":[60,76,140],"has":[62],"been":[63],"applied":[64],"in":[65,69,88],"analysis.":[67],"However,":[68],"study":[71],"combination":[73],"modified":[75,139],"with":[77,90],"Adaptive":[78],"window":[79],"width":[80],"based":[81],"on":[82,137],"Chirp":[84],"Rate,":[85],"termed":[86],"ASTFT,":[87],"conjunction":[89],"Spectrogram":[91],"Features":[92],"proposed":[94],"optimal":[96],"enhancement.":[100],"LibriSpeech":[101],"ASR":[102],"Corpus":[103],"benchmark":[106],"dataset":[107],"experiment.":[110],"spectrum":[112],"from":[113],"enhanced":[115],"Speech":[116],"estimated":[119],"using":[120],"several":[121],"spectrogram":[122],"features":[123],"obtain":[125],"unit":[127],"peak":[128],"amplitude.":[129],"Priori":[130],"Signal-to-Noise":[131],"Ratio":[132],"(SNR)":[133],"estimation":[134],"performed":[136],"signal,":[142],"it":[144],"achieved":[145],"SNR":[147],"31.86":[149],"dB":[150],"which":[151],"considered":[153],"be":[155],"effectively":[157],"clean":[158],"signal.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}