{"id":"https://openalex.org/W4200364421","doi":"https://doi.org/10.1109/waspaa52581.2021.9632786","title":"SIDIQ: Computational Quality Assessment of Enhanced Speech Based on Auditory Figure-Ground Segregation, Similarity, and Disturbance","display_name":"SIDIQ: Computational Quality Assessment of Enhanced Speech Based on Auditory Figure-Ground Segregation, Similarity, and Disturbance","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W4200364421","doi":"https://doi.org/10.1109/waspaa52581.2021.9632786"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa52581.2021.9632786","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632786","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5065188041","display_name":"Benjamin E. Stahl","orcid":"https://orcid.org/0000-0002-3169-3167"},"institutions":[{"id":"https://openalex.org/I317320687","display_name":"University of Music and Performing Arts Graz","ror":"https://ror.org/0541v4g57","country_code":"AT","type":"education","lineage":["https://openalex.org/I317320687"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Benjamin Stahl","raw_affiliation_strings":["University of Music and Performing Arts, Institute of Electronic Music and Acoustics,Graz,Austria,8010"],"affiliations":[{"raw_affiliation_string":"University of Music and Performing Arts, Institute of Electronic Music and Acoustics,Graz,Austria,8010","institution_ids":["https://openalex.org/I317320687"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087260049","display_name":"Alois Sontacchi","orcid":"https://orcid.org/0009-0008-9205-209X"},"institutions":[{"id":"https://openalex.org/I317320687","display_name":"University of Music and Performing Arts Graz","ror":"https://ror.org/0541v4g57","country_code":"AT","type":"education","lineage":["https://openalex.org/I317320687"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Alois Sontacchi","raw_affiliation_strings":["University of Music and Performing Arts, Institute of Electronic Music and Acoustics,Graz,Austria,8010"],"affiliations":[{"raw_affiliation_string":"University of Music and Performing Arts, Institute of Electronic Music and Acoustics,Graz,Austria,8010","institution_ids":["https://openalex.org/I317320687"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065188041"],"corresponding_institution_ids":["https://openalex.org/I317320687"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17484787,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"127","issue":null,"first_page":"96","last_page":"100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9904999732971191,"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/pesq","display_name":"PESQ","score":0.8485004901885986},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7183198928833008},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6073848605155945},{"id":"https://openalex.org/keywords/quality-assessment","display_name":"Quality assessment","score":0.586273729801178},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5636148452758789},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.5489939451217651},{"id":"https://openalex.org/keywords/quality-score","display_name":"Quality Score","score":0.5195363163948059},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47822850942611694},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4625937342643738},{"id":"https://openalex.org/keywords/disturbance","display_name":"Disturbance (geology)","score":0.4140709638595581},{"id":"https://openalex.org/keywords/evaluation-methods","display_name":"Evaluation methods","score":0.34011268615722656},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33005648851394653},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32190847396850586},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.1779317855834961},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.17137488722801208},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.1331925392150879},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10176539421081543},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09830594062805176}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.8485004901885986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7183198928833008},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6073848605155945},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.586273729801178},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5636148452758789},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5489939451217651},{"id":"https://openalex.org/C2779346075","wikidata":"https://www.wikidata.org/wiki/Q7268763","display_name":"Quality Score","level":3,"score":0.5195363163948059},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47822850942611694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4625937342643738},{"id":"https://openalex.org/C2777601987","wikidata":"https://www.wikidata.org/wiki/Q5283581","display_name":"Disturbance (geology)","level":2,"score":0.4140709638595581},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.34011268615722656},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33005648851394653},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32190847396850586},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.1779317855834961},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.17137488722801208},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.1331925392150879},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10176539421081543},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09830594062805176},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa52581.2021.9632786","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632786","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W112201544","https://openalex.org/W165956390","https://openalex.org/W1566138856","https://openalex.org/W1689445748","https://openalex.org/W1728888090","https://openalex.org/W1876052200","https://openalex.org/W1973746598","https://openalex.org/W2017977879","https://openalex.org/W2028138004","https://openalex.org/W2105921478","https://openalex.org/W2108708552","https://openalex.org/W2791686384","https://openalex.org/W2892110446","https://openalex.org/W2953132115","https://openalex.org/W2953384591","https://openalex.org/W2964058413","https://openalex.org/W2998733532","https://openalex.org/W3037038648","https://openalex.org/W4206812624","https://openalex.org/W4253928870","https://openalex.org/W6633767985","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W2352090830","https://openalex.org/W2092382984","https://openalex.org/W2283131058","https://openalex.org/W2466958844","https://openalex.org/W1967325901","https://openalex.org/W2171704044","https://openalex.org/W825444719","https://openalex.org/W2901007863","https://openalex.org/W4234973199","https://openalex.org/W3006139755"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,43,60,108],"new":[4],"method":[5],"to":[6,29,66],"predict":[7],"the":[8,30,74,86],"subjective":[9,47,101],"quality":[10,51,54,68,81,89,97,105],"of":[11,24,76,85],"enhanced":[12],"speech":[13],"called":[14],"Similarity":[15],"Disturbance":[16],"Quality":[17],"(SiDiQ).":[18],"SiDiQ":[19,58,78],"is":[20,107],"based":[21,99],"on":[22,49,59,100,103],"models":[23,39],"auditory":[25],"figure-ground":[26],"segregation,":[27],"similarity":[28],"reference":[31],"stimulus,":[32],"and":[33,52,63,83],"disturbance":[34],"by":[35],"background":[36],"sounds.":[37],"The":[38,92],"were":[40],"parameterized":[41],"in":[42],"data-driven":[44],"way,":[45],"using":[46],"ratings":[48,102],"overall":[50],"single":[53,104],"aspects.":[55],"We":[56],"evaluated":[57],"test":[61],"dataset":[62],"compared":[64],"it":[65],"other":[67],"assessment":[69,90,98],"methods.":[70,91],"Despite":[71],"not":[72],"reaching":[73],"accuracy":[75],"PESQ,":[77],"outperformed":[79],"simple":[80],"metrics":[82],"some":[84],"more":[87],"sophisticated":[88],"results":[93],"show":[94],"that":[95],"computational":[96],"aspects":[106],"promising":[109],"methodical":[110],"framework.":[111]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
