{"id":"https://openalex.org/W2972680448","doi":"https://doi.org/10.21437/interspeech.2019-2898","title":"Improvement and Assessment of Spectro-Temporal Modulation Analysis for Speech Intelligibility Estimation","display_name":"Improvement and Assessment of Spectro-Temporal Modulation Analysis for Speech Intelligibility Estimation","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972680448","doi":"https://doi.org/10.21437/interspeech.2019-2898","mag":"2972680448"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2898","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2898","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://vbn.aau.dk/da/publications/2d87dc56-e754-423f-afb4-f3e993edc4be","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051158946","display_name":"Amin Edraki","orcid":"https://orcid.org/0000-0002-0843-5522"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Amin Edraki","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Queen's University, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Queen's University, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101683153","display_name":"Wai-Yip Chan","orcid":"https://orcid.org/0000-0001-5322-2449"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Wai-Yip Chan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Queen's University, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Queen's University, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101679595","display_name":"Jesper Jensen","orcid":"https://orcid.org/0000-0003-1478-622X"},"institutions":[{"id":"https://openalex.org/I4210166028","display_name":"Oticon (Denmark)","ror":"https://ror.org/05mwsq745","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210166028"]},{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jesper Jensen","raw_affiliation_strings":["Oticon, Denmark","Department of Electronic Systems, Aalborg University, Denmark"],"affiliations":[{"raw_affiliation_string":"Oticon, Denmark","institution_ids":["https://openalex.org/I4210166028"]},{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027014330","display_name":"Daniel Fogerty","orcid":"https://orcid.org/0000-0002-2611-102X"},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Fogerty","raw_affiliation_strings":["Department of Communication Sciences and Disorders, University of South Carolina, USA"],"affiliations":[{"raw_affiliation_string":"Department of Communication Sciences and Disorders, University of South Carolina, USA","institution_ids":["https://openalex.org/I155781252"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051158946"],"corresponding_institution_ids":["https://openalex.org/I204722609"],"apc_list":null,"apc_paid":null,"fwci":0.3317,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55775132,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1378","last_page":"1382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.8273078799247742},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.8066440224647522},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.7654099464416504},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7073620557785034},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.666384220123291},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.49486082792282104},{"id":"https://openalex.org/keywords/amplitude-modulation","display_name":"Amplitude modulation","score":0.47162818908691406},{"id":"https://openalex.org/keywords/frequency-modulation","display_name":"Frequency modulation","score":0.38297244906425476},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.28389033675193787},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19352024793624878},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15263724327087402},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.1299569308757782},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12819477915763855},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06732216477394104}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.8273078799247742},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.8066440224647522},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7654099464416504},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7073620557785034},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.666384220123291},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.49486082792282104},{"id":"https://openalex.org/C201905106","wikidata":"https://www.wikidata.org/wiki/Q183755","display_name":"Amplitude modulation","level":4,"score":0.47162818908691406},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.38297244906425476},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.28389033675193787},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19352024793624878},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15263724327087402},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.1299569308757782},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12819477915763855},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06732216477394104},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2019-2898","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2898","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/2d87dc56-e754-423f-afb4-f3e993edc4be","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/2d87dc56-e754-423f-afb4-f3e993edc4be","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Edraki, A, Chan, W Y G, Jensen, J & Fogerty, D 2019, Improvement and Assessment of Spectro-Temporal Modulation Analysis for Speech Intelligibility Estimation. in Interspeech 2019. vol. 2019-September, ISCA, Proceedings of the International Conference on Spoken Language Processing, pp. 1378-1382, Interspeech 2019 , Graz, Austria, 15/09/2019. https://doi.org/10.21437/Interspeech.2019-2898","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/2d87dc56-e754-423f-afb4-f3e993edc4be","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/2d87dc56-e754-423f-afb4-f3e993edc4be","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Edraki, A, Chan, W Y G, Jensen, J & Fogerty, D 2019, Improvement and Assessment of Spectro-Temporal Modulation Analysis for Speech Intelligibility Estimation. in Interspeech 2019. vol. 2019-September, ISCA, Proceedings of the International Conference on Spoken Language Processing, pp. 1378-1382, Interspeech 2019 , Graz, Austria, 15/09/2019. https://doi.org/10.21437/Interspeech.2019-2898","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1990934990","https://openalex.org/W1999686891","https://openalex.org/W2015512175","https://openalex.org/W2023262923","https://openalex.org/W2030680983","https://openalex.org/W2054139811","https://openalex.org/W2070154210","https://openalex.org/W2082668798","https://openalex.org/W2087126002","https://openalex.org/W2125114513","https://openalex.org/W2129715180","https://openalex.org/W2132606418","https://openalex.org/W2141998673","https://openalex.org/W2516001803","https://openalex.org/W2800640015","https://openalex.org/W4255474605"],"related_works":["https://openalex.org/W4236245227","https://openalex.org/W2068642629","https://openalex.org/W2004723848","https://openalex.org/W2093157008","https://openalex.org/W2012415775","https://openalex.org/W2070091937","https://openalex.org/W2143773860","https://openalex.org/W2060366623","https://openalex.org/W2054254129","https://openalex.org/W2037608065"],"abstract_inverted_index":{"Several":[0],"recent":[1],"high-performing":[2,67],"intelligibility":[3,36,60],"estimators":[4,71],"of":[5,21,53,74],"acoustically":[6],"degraded":[7],"speech":[8,29,35],"signals":[9],"employ":[10],"temporal":[11],"modulation":[12,47,94],"analysis.":[13,48],"In":[14],"this":[15],"paper,":[16],"we":[17],"investigate":[18],"the":[19,54,70,75],"utility":[20],"using":[22],"both":[23,84],"spectro-":[24],"and":[25,57,78,86,106],"temporal-modulation":[26],"for":[27,98],"estimating":[28],"intelligibility.":[30],"We":[31,49],"modified":[32,55],"a":[33],"pre-existing":[34],"estimation":[37],"scheme":[38],"(STMI)":[39],"that":[40,92],"was":[41],"inspired":[42],"by":[43],"human":[44],"auditory":[45],"spectro-temporal":[46,93],"produced":[50],"several":[51,66],"variants":[52,77],"STMI":[56,76],"assessed":[58],"their":[59],"prediction":[61],"accuracy,":[62],"in":[63],"comparison":[64],"with":[65],"estimators.":[68],"Among":[69],"tested,":[72],"one":[73],"eSTOI":[79],"performed":[80],"consistently":[81],"well":[82],"on":[83],"noisy":[85],"reverberated":[87],"speech.":[88],"These":[89],"results":[90],"suggest":[91],"analysis":[95],"is":[96],"useful":[97],"certain":[99],"degradation":[100],"conditions":[101],"such":[102],"as":[103],"modulated":[104],"noise":[105],"reverberation.":[107]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}