{"id":"https://openalex.org/W3097278534","doi":"https://doi.org/10.21437/interspeech.2020-1885","title":"Exploration of Audio Quality Assessment and Anomaly Localisation Using Attention Models","display_name":"Exploration of Audio Quality Assessment and Anomaly Localisation Using Attention Models","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3097278534","doi":"https://doi.org/10.21437/interspeech.2020-1885","mag":"3097278534"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1885","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","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/A5013817745","display_name":"Qiang Huang","orcid":"https://orcid.org/0000-0003-1120-4685"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qiang Huang","raw_affiliation_strings":["Depart of Computer Science, University of Sheffield Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Depart of Computer Science, University of Sheffield Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030528300","display_name":"Thomas Hain","orcid":"https://orcid.org/0000-0003-0939-3464"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Hain","raw_affiliation_strings":["Depart of Computer Science, University of Sheffield Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Depart of Computer Science, University of Sheffield Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12814714,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4611","last_page":"4615"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9722999930381775,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8229269981384277},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6351479291915894},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6307868361473083},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6014031171798706},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5498231053352356},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5471954345703125},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.5252460837364197},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.5036644339561462},{"id":"https://openalex.org/keywords/quality-score","display_name":"Quality Score","score":0.4649127125740051},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.46391406655311584},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.441048264503479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4236820340156555},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3608967661857605},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.17538368701934814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8229269981384277},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6351479291915894},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6307868361473083},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6014031171798706},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5498231053352356},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5471954345703125},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.5252460837364197},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.5036644339561462},{"id":"https://openalex.org/C2779346075","wikidata":"https://www.wikidata.org/wiki/Q7268763","display_name":"Quality Score","level":3,"score":0.4649127125740051},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46391406655311584},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.441048264503479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4236820340156555},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3608967661857605},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.17538368701934814},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1885","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1762161369","https://openalex.org/W1975163393","https://openalex.org/W2131774270","https://openalex.org/W2133564696","https://openalex.org/W2219249508","https://openalex.org/W2561217444","https://openalex.org/W2594990650","https://openalex.org/W2603567530","https://openalex.org/W2765278963","https://openalex.org/W2766219058","https://openalex.org/W2766798784","https://openalex.org/W2889519245","https://openalex.org/W2921144622","https://openalex.org/W2963403924","https://openalex.org/W2970827607","https://openalex.org/W2972369255","https://openalex.org/W2976556660","https://openalex.org/W3015412845","https://openalex.org/W3025783616","https://openalex.org/W3100777112","https://openalex.org/W3127686677","https://openalex.org/W4246410698","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2033549879","https://openalex.org/W2013629269","https://openalex.org/W2096935541","https://openalex.org/W4221158116","https://openalex.org/W2943685190","https://openalex.org/W4391020683","https://openalex.org/W3027116454","https://openalex.org/W2986204340","https://openalex.org/W3047188278","https://openalex.org/W4304098873"],"abstract_inverted_index":{"Many":[0],"applications":[1],"of":[2,12,15,27,150],"speech":[3],"technology":[4],"require":[5],"more":[6,8],"and":[7,32,62,81,106,129,159,173,178],"audio":[9,50],"data.Automatic":[10],"assessment":[11,35,52],"the":[13,16,25,28,82,101,130,148],"quality":[14,51,127],"collected":[17],"recordings":[18],"is":[19,53,67,84,104,122,132],"important":[20],"to":[21,68,75,85,123,133],"ensure":[22],"they":[23],"meet":[24],"requirements":[26],"related":[29,95],"applications.However,":[30],"effective":[31],"high":[33],"performing":[34],"remains":[36],"a":[37,41,46,70,79,142,155],"challenging":[38],"task":[39,121],"without":[40],"clean":[42],"reference.In":[43],"this":[44],"paper,":[45],"novel":[47],"model":[48],"for":[49],"proposed":[54,99,152],"by":[55,92,108,167],"jointly":[56],"using":[57],"bidirectional":[58],"long":[59],"short-term":[60],"memory":[61],"an":[63,125,136],"attention":[64],"mechanism.The":[65],"former":[66],"mimic":[69],"human":[71],"auditory":[72],"perception":[73],"ability":[74],"learn":[76],"information":[77],"from":[78,89],"recording,":[80],"latter":[83],"further":[86],"discriminate":[87],"interferences":[88],"desired":[90],"signals":[91],"highlighting":[93],"target":[94],"features.To":[96],"evaluate":[97],"our":[98,114,151],"approach,":[100],"TIMIT":[102],"dataset":[103],"used":[105],"augmented":[107],"mixing":[109],"with":[110],"various":[111],"natural":[112],"sounds.In":[113],"experiments,":[115],"two":[116],"tasks":[117],"are":[118],"explored.The":[119],"first":[120],"predict":[124],"utterance":[126],"score,":[128],"second":[131],"identify":[134],"where":[135],"anomalous":[137],"distortion":[138],"takes":[139],"place":[140],"in":[141],"recording.The":[143],"obtained":[144],"results":[145],"show":[146],"that":[147],"use":[149],"approach":[153],"outperforms":[154],"strong":[156],"baseline":[157],"method":[158],"gains":[160],"about":[161],"5%":[162],"improvements":[163],"after":[164],"being":[165],"measured":[166],"three":[168],"metrics,":[169],"Linear":[170],"Correlation":[171,176],"Coefficient":[172],"Spearman's":[174],"Rank":[175],"Coefficient,":[177],"F1.":[179]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}