{"id":"https://openalex.org/W2136024641","doi":"https://doi.org/10.1109/mmsp.2004.1436570","title":"Speech quality measure based on auditory scene analysis","display_name":"Speech quality measure based on auditory scene analysis","publication_year":2005,"publication_date":"2005-06-07","ids":{"openalex":"https://openalex.org/W2136024641","doi":"https://doi.org/10.1109/mmsp.2004.1436570","mag":"2136024641"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2004.1436570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2004.1436570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE 6th Workshop on Multimedia Signal Processing, 2004.","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/A5100701774","display_name":"Shyam Srinivasan","orcid":"https://orcid.org/0000-0002-8069-5628"},"institutions":[{"id":"https://openalex.org/I4210146082","display_name":"Sify Technologies (India)","ror":"https://ror.org/03r8r2789","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210146082"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"S.H. Srinivasan","raw_affiliation_strings":["Applied Research Group, Satyam Computer Services Limited, Bangalore, India","Appl. Res. Group, Satyam Comput. Services Ltd., Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Applied Research Group, Satyam Computer Services Limited, Bangalore, India","institution_ids":["https://openalex.org/I4210146082"]},{"raw_affiliation_string":"Appl. Res. Group, Satyam Comput. Services Ltd., Bangalore, India","institution_ids":["https://openalex.org/I4210146082"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100701774"],"corresponding_institution_ids":["https://openalex.org/I4210146082"],"apc_list":null,"apc_paid":null,"fwci":0.3179,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60007734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"50","issue":null,"first_page":"371","last_page":"374"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9980999827384949,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7986219525337219},{"id":"https://openalex.org/keywords/psychoacoustics","display_name":"Psychoacoustics","score":0.741466224193573},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.7391701936721802},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.678363561630249},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6418429613113403},{"id":"https://openalex.org/keywords/psqm","display_name":"PSQM","score":0.5660543441772461},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.48123812675476074},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4482472538948059},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.43748739361763},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.37822023034095764},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.37319716811180115},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1335391104221344},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12597638368606567},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08059123158454895},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.07837292551994324},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07166609168052673}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986219525337219},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.741466224193573},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.7391701936721802},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.678363561630249},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6418429613113403},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.5660543441772461},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.48123812675476074},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4482472538948059},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.43748739361763},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37822023034095764},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.37319716811180115},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1335391104221344},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12597638368606567},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08059123158454895},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.07837292551994324},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07166609168052673},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/mmsp.2004.1436570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2004.1436570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE 6th Workshop on Multimedia Signal Processing, 2004.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1606614440","https://openalex.org/W1789794644","https://openalex.org/W2170057365","https://openalex.org/W2222512263","https://openalex.org/W2294106860","https://openalex.org/W2478203769","https://openalex.org/W4210981656","https://openalex.org/W4256399001","https://openalex.org/W6636106077","https://openalex.org/W6638142982"],"related_works":["https://openalex.org/W4319347033","https://openalex.org/W1890431648","https://openalex.org/W2020464095","https://openalex.org/W137020845","https://openalex.org/W2106874932","https://openalex.org/W1911859126","https://openalex.org/W4386752790","https://openalex.org/W2365485488","https://openalex.org/W2040374013","https://openalex.org/W2151333624"],"abstract_inverted_index":{"Objective":[0],"speech":[1,9,15,37],"quality":[2,16,38],"measures":[3,17],"are":[4,18,54],"very":[5],"important":[6],"for":[7],"evaluating":[8],"codecs":[10],"and":[11,46,51],"VoIP":[12],"systems.":[13],"Recent":[14],"based":[19],"on":[20],"psychoacoustic":[21],"facts.":[22],"In":[23],"this":[24],"paper":[25],"we":[26],"incorporate":[27],"ideas":[28],"from":[29],"auditory":[30],"scene":[31],"analysis":[32],"in":[33],"the":[34],"computation":[35],"of":[36,43],"measure.":[39],"Specifically,":[40],"use":[41],"notions":[42],"harmonicity,":[44],"dynamics,":[45],"onset":[47],"times.":[48],"Both":[49],"relative":[50],"absolute":[52],"metrics":[53],"proposed.":[55]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}