{"id":"https://openalex.org/W4386098783","doi":"https://doi.org/10.1145/3605549","title":"Speech Feature Enhancement based on Time-frequency Analysis","display_name":"Speech Feature Enhancement based on Time-frequency Analysis","publication_year":2023,"publication_date":"2023-08-23","ids":{"openalex":"https://openalex.org/W4386098783","doi":"https://doi.org/10.1145/3605549"},"language":"en","primary_location":{"id":"doi:10.1145/3605549","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3605549","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-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/A5049682757","display_name":"Hao D.","orcid":"https://orcid.org/0000-0002-9014-1506"},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Duc-Hao Do","raw_affiliation_strings":["University of Science, Vietnam National University, and FPT University, Vietnam"],"raw_orcid":"https://orcid.org/0000-0002-9014-1506","affiliations":[{"raw_affiliation_string":"University of Science, Vietnam National University, and FPT University, Vietnam","institution_ids":["https://openalex.org/I109689652"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008731646","display_name":"Thanh-Duc Chau","orcid":"https://orcid.org/0009-0000-4877-2649"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thanh-Duc Chau","raw_affiliation_strings":["University of Science, and Vietnam National University, Vietnam"],"raw_orcid":"https://orcid.org/0009-0000-4877-2649","affiliations":[{"raw_affiliation_string":"University of Science, and Vietnam National University, Vietnam","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067418754","display_name":"Tr\u1ea7n Th\u00e1i S\u01a1n","orcid":"https://orcid.org/0000-0002-4063-7095"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thai-Son Tran","raw_affiliation_strings":["University of Science, and Vietnam National University, Vietnam"],"raw_orcid":"https://orcid.org/0000-0002-4063-7095","affiliations":[{"raw_affiliation_string":"University of Science, and Vietnam National University, Vietnam","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.174,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4032144,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"22","issue":"8","first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9962999820709229,"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":0.9962999820709229,"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":0.9894999861717224,"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":0.974399983882904,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7477177977561951},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7065156102180481},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6971900463104248},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6806275844573975},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5959635972976685},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5687285661697388},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5623274445533752},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.525945246219635},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.525867223739624},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5240938067436218},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.5219249725341797},{"id":"https://openalex.org/keywords/time\u2013frequency-representation","display_name":"Time\u2013frequency representation","score":0.5122200846672058},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.4995737075805664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.482214093208313},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.12439113855361938},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0988314151763916}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7477177977561951},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7065156102180481},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6971900463104248},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6806275844573975},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5959635972976685},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5687285661697388},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5623274445533752},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.525945246219635},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.525867223739624},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5240938067436218},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.5219249725341797},{"id":"https://openalex.org/C124062153","wikidata":"https://www.wikidata.org/wiki/Q7806645","display_name":"Time\u2013frequency representation","level":4,"score":0.5122200846672058},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4995737075805664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.482214093208313},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.12439113855361938},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0988314151763916},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3605549","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3605549","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320318839","display_name":"T\u1eadp \u0111o\u00e0n Vingroup - C\u00f4ng ty CP","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1553255015","https://openalex.org/W1761200639","https://openalex.org/W1954839664","https://openalex.org/W2018363392","https://openalex.org/W2041964370","https://openalex.org/W2044142910","https://openalex.org/W2084123349","https://openalex.org/W2090218979","https://openalex.org/W2097530131","https://openalex.org/W2100159550","https://openalex.org/W2117761544","https://openalex.org/W2126526582","https://openalex.org/W2140147143","https://openalex.org/W2147800946","https://openalex.org/W2435725855","https://openalex.org/W2798905217","https://openalex.org/W2921245937","https://openalex.org/W2959140451","https://openalex.org/W3097183635","https://openalex.org/W3178522489","https://openalex.org/W3209216890","https://openalex.org/W3213113284","https://openalex.org/W4297902869"],"related_works":["https://openalex.org/W2753718322","https://openalex.org/W2391512568","https://openalex.org/W2595784504","https://openalex.org/W4241783057","https://openalex.org/W2148268314","https://openalex.org/W2493476589","https://openalex.org/W2376948258","https://openalex.org/W2354116838","https://openalex.org/W2381035110","https://openalex.org/W1975700579"],"abstract_inverted_index":{"Time-frequency":[0],"analysis":[1],"(TFA)":[2],"is":[3,36,128],"a":[4,50,74,79,110,119],"powerful":[5],"method":[6,108],"to":[7,26,48,57,77,134,152,158],"exploit":[8],"the":[9,28,54,59,64,68,84,90,104,106,131,136,140,154],"hidden":[10],"information":[11,151],"of":[12,81],"signals,":[13],"including":[14],"speech":[15,35,65,143],"signals.":[16],"Many":[17],"techniques":[18],"in":[19,67,92,113,161],"this":[20],"group":[21],"were":[22],"invented":[23],"and":[24,39,61,166],"developed":[25],"capture":[27],"most":[29],"crucial":[30],"stationary":[31],"feature.":[32],"However,":[33],"human":[34],"not":[37],"stable,":[38],"it":[40],"contains":[41,149],"some":[42],"non-stationary":[43],"elements.":[44],"This":[45],"work":[46],"aims":[47],"design":[49,73],"new":[51,75],"algorithm":[52,76],"via":[53,97],"TFA":[55],"technique":[56],"extract":[58],"trends":[60],"changes":[62],"inside":[63],"signal":[66,85,91],"time-frequency":[69],"(TF)":[70],"plane.":[71],"We":[72],"create":[78],"set":[80],"atoms":[82],"for":[83,142],"transform,":[86],"which":[87,114],"can":[88],"analyze":[89],"many":[93],"different":[94],"view":[95],"directions":[96],"Poly-Linear":[98],"Chirplet":[99,122],"Transform":[100,123],"(PLCT).":[101],"After":[102],"processing":[103],"signal,":[105],"proposed":[107],"returns":[109],"multichannel":[111],"output":[112],"each":[115],"channel":[116],"results":[117,156],"from":[118],"particular":[120],"Linear":[121],"(LCT).":[124],"The":[125],"feature":[126,133,148],"then":[127],"combined":[129],"with":[130],"MFCC":[132],"form":[135],"final":[137],"representation.":[138],"Although":[139],"size":[141],"representation":[144],"rises,":[145],"our":[146],"extracted":[147],"rich-meaning":[150],"improve":[153],"recognition":[155],"compared":[157],"other":[159],"features":[160],"gender":[162],"recognition,":[163,165],"dialect":[164],"speaker":[167],"recognition.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}