{"id":"https://openalex.org/W6946068668","doi":"https://doi.org/10.26190/unsworks/17712","title":"Audio compression and speech enhancement using temporal masking models","display_name":"Audio compression and speech enhancement using temporal masking models","publication_year":2022,"publication_date":"2022-03-21","ids":{"openalex":"https://openalex.org/W6946068668","doi":"https://doi.org/10.26190/unsworks/17712"},"language":"en","primary_location":{"id":"pmh:oai:unsworks.library.unsw.edu.au:1959.4/40485","is_oa":true,"landing_page_url":"http://hdl.handle.net/1959.4/40485","pdf_url":"https://unsworks.unsw.edu.au/bitstreams/0f862bf6-828c-4d29-b3e4-075b35a812ca/download","source":{"id":"https://openalex.org/S4306401737","display_name":"UNSWorks (University of New South Wales, Sydney, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40053085","host_organization_name":"Australian Defence Force Academy","host_organization_lineage":["https://openalex.org/I40053085"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"http://purl.org/coar/resource_type/c_db06"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://unsworks.unsw.edu.au/bitstreams/0f862bf6-828c-4d29-b3e4-075b35a812ca/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Gunawan, Teddy Surya","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gunawan, Teddy Surya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.04560000076889992,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.04560000076889992,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T13568","display_name":"Wood and Agarwood Research","score":0.042500000447034836,"subfield":{"id":"https://openalex.org/subfields/1605","display_name":"Organic Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.03840000182390213,"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/auditory-masking","display_name":"Auditory masking","score":0.774399995803833},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.7670000195503235},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.6158000230789185},{"id":"https://openalex.org/keywords/psychoacoustics","display_name":"Psychoacoustics","score":0.5993000268936157},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5460000038146973},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5131999850273132},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.453000009059906},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3774000108242035},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.365200012922287}],"concepts":[{"id":"https://openalex.org/C77801330","wikidata":"https://www.wikidata.org/wiki/Q1363413","display_name":"Auditory masking","level":3,"score":0.774399995803833},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.7670000195503235},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7452999949455261},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6883000135421753},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.6158000230789185},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.5993000268936157},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5460000038146973},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5131999850273132},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.453000009059906},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3774000108242035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.375900000333786},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.365200012922287},{"id":"https://openalex.org/C98526533","wikidata":"https://www.wikidata.org/wiki/Q1691938","display_name":"Sub-band coding","level":3,"score":0.32839998602867126},{"id":"https://openalex.org/C150178126","wikidata":"https://www.wikidata.org/wiki/Q18433212","display_name":"Dynamic range compression","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.2971999943256378},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2842000126838684},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2786000072956085},{"id":"https://openalex.org/C2776817677","wikidata":"https://www.wikidata.org/wiki/Q4839818","display_name":"Backward masking","level":3,"score":0.2734000086784363},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:unsworks.library.unsw.edu.au:1959.4/40485","is_oa":true,"landing_page_url":"http://hdl.handle.net/1959.4/40485","pdf_url":"https://unsworks.unsw.edu.au/bitstreams/0f862bf6-828c-4d29-b3e4-075b35a812ca/download","source":{"id":"https://openalex.org/S4306401737","display_name":"UNSWorks (University of New South Wales, Sydney, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40053085","host_organization_name":"Australian Defence Force Academy","host_organization_lineage":["https://openalex.org/I40053085"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"http://purl.org/coar/resource_type/c_db06"},{"id":"pmh:oai:unsworks.unsw.edu.au:1959.4/40485","is_oa":false,"landing_page_url":"http://handle.unsw.edu.au/1959.4/40485","pdf_url":null,"source":{"id":"https://openalex.org/S4377196481","display_name":"UNSWorks (UNSW Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31746571","host_organization_name":"UNSW Sydney","host_organization_lineage":["https://openalex.org/I31746571"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},{"id":"doi:10.26190/unsworks/17712","is_oa":true,"landing_page_url":"https://doi.org/10.26190/unsworks/17712","pdf_url":null,"source":{"id":"https://openalex.org/S7407053176","display_name":"University of New South Wales","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dissertation"}],"best_oa_location":{"id":"pmh:oai:unsworks.library.unsw.edu.au:1959.4/40485","is_oa":true,"landing_page_url":"http://hdl.handle.net/1959.4/40485","pdf_url":"https://unsworks.unsw.edu.au/bitstreams/0f862bf6-828c-4d29-b3e4-075b35a812ca/download","source":{"id":"https://openalex.org/S4306401737","display_name":"UNSWorks (University of New South Wales, Sydney, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40053085","host_organization_name":"Australian Defence Force Academy","host_organization_lineage":["https://openalex.org/I40053085"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"http://purl.org/coar/resource_type/c_db06"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.41184985637664795}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6946068668.pdf","grobid_xml":"https://content.openalex.org/works/W6946068668.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Of":[0],"the":[1,23,28,32,35,50,55,77,82,103,122,157,185,206,256,268,281,284],"few":[2],"existing":[3,146],"models":[4,40,48,114],"of":[5,31,37,49,54,81,121,140,210,301],"temporal":[6,51,78,106,189,290,308],"masking":[7,52,79,90,107,113,174,190,208,232,265,291],"applicable":[8],"to":[9,167],"problems":[10],"such":[11],"as":[12,240],"compression":[13,64,71],"and":[14,59,65,109,130,188,227,235,249,299],"enhancement,":[15],"none":[16],"are":[17],"based":[18,260],"on":[19,88,261,280],"empirical":[20],"data":[21,33],"from":[22],"psychoacoustic":[24],"literature,":[25],"presumably":[26],"because":[27],"multidimensional":[29],"nature":[30],"makes":[34],"derivation":[36],"tractable":[38],"functional":[39,47],"difficult.":[41],"This":[42],"thesis":[43],"presents":[44],"two":[45],"new":[46,264],"effect":[53],"human":[56,83,211,305],"auditory":[57,84,207,212,306],"system,":[58,85],"their":[60,238],"exploitation":[61],"in":[62,115],"audio":[63,70,96,149,181,312],"speech":[66,202,271,286,314],"enhancement":[67,203,258,272,287],"applications.":[68],"Traditional":[69],"algorithms":[72,204,226],"do":[73],"not":[74],"completely":[75],"utilise":[76],"properties":[80],"relying":[86],"solely":[87],"simultaneous":[89,112,147,231,310],"models.":[91],"A":[92],"perceptual":[93],"wavelet":[94,159],"packet-based":[95],"coder":[97,123],"has":[98,163,191,293],"been":[99,164,192],"devised":[100],"that":[101,214,229,255],"incorporates":[102],"first":[104],"developed":[105],"model":[108],"combined":[110],"with":[111,145],"a":[116,137,178,197,262],"novel":[117],"manner.":[118],"An":[119],"evaluation":[120],"using":[124,184,245],"both":[125],"objective":[126,318],"(PEAQ,":[127],"ITU-R":[128],"BS.1387)":[129],"extensive":[131],"subjective":[132,250,316],"tests":[133],"(ITU-R":[134],"BS.1116)":[135],"revealed":[136],"bitrate":[138],"reduction":[139],"more":[141,172],"than":[142],"17%":[143],"compared":[144],"masking-based":[148],"coders,":[150],"while":[151],"preserving":[152],"transparent":[153],"quality.":[154],"In":[155],"addition,":[156],"oversampled":[158],"packet":[160],"transform":[161],"(ODWT)":[162],"newly":[165],"applied":[166],"obtain":[168],"alias-free":[169],"coefficients":[170],"for":[171,200,237],"accurate":[173],"threshold":[175],"calculation.":[176],"Finally,":[177],"low-complexity":[179],"scalable":[180],"coding":[182],"algorithm":[183],"ODWT-based":[186],"thresholds":[187],"investigated.":[193],"Currently,":[194],"there":[195],"is":[196],"strong":[198],"need":[199],"innovative":[201],"exploiting":[205,289],"effects":[209,292],"system":[213],"perform":[215],"well":[216],"at":[217,275],"very":[218],"low":[219],"signal-to-noise":[220],"ratio.":[221],"Existing":[222],"competitive":[223],"noise":[224],"suppression":[225],"those":[228],"incorporate":[230],"were":[233],"examined":[234],"evaluated":[236],"suitability":[239],"baseline":[241,270],"algorithms.":[242],"Objective":[243],"measures":[244,251],"PESQ":[246],"(ITU-T":[247,252],"P.862)":[248],"P.835)":[253],"demonstrate":[254],"proposed":[257,285],"scheme,":[259],"second":[263],"model,":[266],"outperformed":[267],"seven":[269],"methods":[273],"by":[274],"least":[276],"6-":[277],"20%":[278],"depending":[279],"SNR.":[282],"Hence,":[283],"scheme":[288],"good":[294],"potential":[295],"across":[296],"many":[297],"types":[298],"intensities":[300],"environmental":[302],"noise.":[303],"Keywords:":[304],"system;":[307],"masking;":[309,311],"compression;":[313],"enhancement;":[315],"test;":[317],"test.":[319]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-17T05:52:16.776730","created_date":"2025-10-10T00:00:00"}