{"id":"https://openalex.org/W2107604271","doi":"https://doi.org/10.1109/icassp.2009.4959509","title":"A modified distortion metric for audio coding","display_name":"A modified distortion metric for audio coding","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2107604271","doi":"https://doi.org/10.1109/icassp.2009.4959509","mag":"2107604271"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4959509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959509","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-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/A5060036035","display_name":"Vinay Melkote","orcid":null},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vinay Melkote","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA, USA","Department of Electrical and Computer Engineering, University of California, Santa Barbara, 93106, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Santa Barbara, 93106, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026459097","display_name":"Kenneth Rose","orcid":"https://orcid.org/0000-0001-9463-2647"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenneth Rose","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA, USA","Department of Electrical and Computer Engineering, University of California, Santa Barbara, 93106, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Santa Barbara, 93106, USA","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5060036035"],"corresponding_institution_ids":["https://openalex.org/I154570441"],"apc_list":null,"apc_paid":null,"fwci":1.4284,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81133952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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":0.9991000294685364,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11034","display_name":"Digital Filter Design and Implementation","score":0.9984999895095825,"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/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.7385956048965454},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.6335829496383667},{"id":"https://openalex.org/keywords/modified-discrete-cosine-transform","display_name":"Modified discrete cosine transform","score":0.6267383098602295},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5867550373077393},{"id":"https://openalex.org/keywords/transform-coding","display_name":"Transform coding","score":0.5473863482475281},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.542249321937561},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5319212675094604},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5290809273719788},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5258805751800537},{"id":"https://openalex.org/keywords/lapped-transform","display_name":"Lapped transform","score":0.4872685670852661},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.46341460943222046},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.42026591300964355},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40542829036712646},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37430793046951294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.298025518655777},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2979070246219635},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0855717658996582},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07069265842437744},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06716349720954895}],"concepts":[{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.7385956048965454},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.6335829496383667},{"id":"https://openalex.org/C28726691","wikidata":"https://www.wikidata.org/wiki/Q1268231","display_name":"Modified discrete cosine transform","level":5,"score":0.6267383098602295},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5867550373077393},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.5473863482475281},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.542249321937561},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5319212675094604},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5290809273719788},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5258805751800537},{"id":"https://openalex.org/C91458471","wikidata":"https://www.wikidata.org/wiki/Q17096468","display_name":"Lapped transform","level":5,"score":0.4872685670852661},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.46341460943222046},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.42026591300964355},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40542829036712646},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37430793046951294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.298025518655777},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2979070246219635},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0855717658996582},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07069265842437744},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06716349720954895},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2009.4959509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959509","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.216.5917","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.216.5917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.scl.ece.ucsb.edu/pubs/pubs_E/e09_1.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1550479430","https://openalex.org/W1670669358","https://openalex.org/W2027735369","https://openalex.org/W2115002753","https://openalex.org/W2120611566","https://openalex.org/W2141506761","https://openalex.org/W6633123850"],"related_works":["https://openalex.org/W2978563117","https://openalex.org/W2046080157","https://openalex.org/W2169808749","https://openalex.org/W2556691706","https://openalex.org/W2100383613","https://openalex.org/W2138702206","https://openalex.org/W2135904135","https://openalex.org/W1908108260","https://openalex.org/W3140834049","https://openalex.org/W1967066785"],"abstract_inverted_index":{"Current":[0],"audio":[1,15],"coding":[2],"standards":[3],"employ":[4],"the":[5,21,41,55,60,70,80,87,118],"modified":[6,97,106],"discrete":[7,107],"cosine":[8],"transform":[9,109],"(MDCT)":[10],"where":[11],"overlapped":[12],"frames":[13],"of":[14,50,54,82,92,126],"are":[16,26,74],"windowed":[17],"and":[18,48,84],"transformed":[19],"to":[20,30,36,78],"frequency":[22],"domain.":[23],"Encoding":[24],"parameters":[25],"chosen":[27],"so":[28],"as":[29],"minimize":[31],"a":[32,37,96],"distortion":[33,65,98,120],"measure":[34],"subject":[35],"rate":[38],"constraint.":[39],"At":[40],"decoder,":[42],"inverse":[43],"transformation":[44],"involves":[45],"additional":[46],"windowing":[47,83],"overlap-add":[49,85],"frames.":[51],"An":[52],"analysis":[53],"time":[56],"domain":[57,72],"error":[58,73],"in":[59,75],"reconstructed":[61,127],"frame":[62],"reveals":[63],"that":[64,100],"metrics":[66],"based":[67],"solely":[68],"on":[69],"MDCT":[71],"fact":[76],"unable":[77],"capture":[79,102],"effects":[81,104],"at":[86],"decoder.":[88],"The":[89],"main":[90],"contribution":[91],"this":[93],"paper":[94],"is":[95],"metric":[99,121],"does":[101],"these":[103],"via":[105],"sine":[108],"analysis.":[110],"When":[111],"incorporated":[112],"into":[113],"an":[114],"Advanced":[115],"Audio":[116],"Coder":[117],"proposed":[119],"significantly":[122],"improves":[123],"subjective":[124],"quality":[125],"audio.":[128]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
