{"id":"https://openalex.org/W4390548162","doi":"https://doi.org/10.1145/3632410.3632413","title":"An Approach for Speech Enhancement in Low SNR Environments using Granular Speaker Embedding","display_name":"An Approach for Speech Enhancement in Low SNR Environments using Granular Speaker Embedding","publication_year":2024,"publication_date":"2024-01-03","ids":{"openalex":"https://openalex.org/W4390548162","doi":"https://doi.org/10.1145/3632410.3632413"},"language":"en","primary_location":{"id":"doi:10.1145/3632410.3632413","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3632410.3632413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)","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/A5069015748","display_name":"Jayasree Saha","orcid":"https://orcid.org/0000-0002-0839-1849"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jayasree Saha","raw_affiliation_strings":["IIIT-H, India"],"affiliations":[{"raw_affiliation_string":"IIIT-H, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007660270","display_name":"Rudrabha Mukhopadhyay","orcid":"https://orcid.org/0009-0000-6628-7065"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rudrabha Mukhopadhyay","raw_affiliation_strings":["IIIT-H, India"],"affiliations":[{"raw_affiliation_string":"IIIT-H, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103069773","display_name":"Aparna Agrawal","orcid":"https://orcid.org/0009-0009-7862-2428"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aparna Agrawal","raw_affiliation_strings":["IIIT-H, India"],"affiliations":[{"raw_affiliation_string":"IIIT-H, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091529242","display_name":"S.C. Jain","orcid":"https://orcid.org/0009-0000-2499-2751"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Surabhi Jain","raw_affiliation_strings":["IIIT-H, India"],"affiliations":[{"raw_affiliation_string":"IIIT-H, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053112307","display_name":"C. V. Jawahar","orcid":"https://orcid.org/0000-0001-6767-7057"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"C. V. Jawahar","raw_affiliation_strings":["IIIT-H, India"],"affiliations":[{"raw_affiliation_string":"IIIT-H, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5069015748"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.375,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47965521,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"325","last_page":"331"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","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/speech-enhancement","display_name":"Speech enhancement","score":0.8208106756210327},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7269690036773682},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7114371657371521},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.593285083770752},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5699996948242188},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5211055874824524},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.49504604935646057},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.4897425174713135},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4332554042339325},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4249623417854309},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29029059410095215},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.21633502840995789},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1231030523777008},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12268361449241638},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06368619203567505}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.8208106756210327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7269690036773682},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7114371657371521},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.593285083770752},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5699996948242188},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5211055874824524},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.49504604935646057},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.4897425174713135},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4332554042339325},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4249623417854309},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29029059410095215},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.21633502840995789},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1231030523777008},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12268361449241638},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06368619203567505},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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:10.1145/3632410.3632413","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3632410.3632413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)","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":19,"referenced_works":["https://openalex.org/W2115973835","https://openalex.org/W2120847449","https://openalex.org/W2141998673","https://openalex.org/W2625477228","https://openalex.org/W2802304149","https://openalex.org/W2915722758","https://openalex.org/W2952218014","https://openalex.org/W3094932283","https://openalex.org/W3095057960","https://openalex.org/W3097756030","https://openalex.org/W3097945073","https://openalex.org/W3099330747","https://openalex.org/W3129077738","https://openalex.org/W3149794337","https://openalex.org/W3206996142","https://openalex.org/W3209059054","https://openalex.org/W4243020849","https://openalex.org/W4296069339","https://openalex.org/W4297841734"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2955597484","https://openalex.org/W2294333436","https://openalex.org/W2653598178","https://openalex.org/W2373767407","https://openalex.org/W3110551121","https://openalex.org/W2131486661","https://openalex.org/W4252682934","https://openalex.org/W2851491717","https://openalex.org/W4200596008"],"abstract_inverted_index":{"The":[0,90],"proliferation":[1],"of":[2],"speech":[3,14,31,57,74,106],"technology":[4,107],"applications":[5],"has":[6],"led":[7],"to":[8,30,83],"an":[9],"unprecedented":[10],"demand":[11],"for":[12,35],"effective":[13],"enhancement":[15],"techniques,":[16],"particularly":[17],"in":[18,79,86,96,105],"low":[19,37,87,102],"Signal-to-Noise":[20],"Ratio":[21],"(SNR)":[22],"conditions.":[23],"This":[24],"research":[25],"presents":[26],"a":[27,47,66],"novel":[28],"approach":[29],"enhancement,":[32],"specifically":[33],"designed":[34],"very":[36],"SNR":[38,88,103],"scenarios.":[39],"Our":[40],"technique":[41,92],"focuses":[42],"on":[43,55],"speaker":[44],"embedding":[45],"at":[46],"granular":[48],"level":[49],"and":[50,59,76],"highlights":[51],"its":[52],"consistent":[53],"impact":[54],"enhancing":[56],"quality":[58,75],"improving":[60],"Automatic":[61],"Speech":[62],"Recognition":[63],"(ASR)":[64],"performance,":[65],"significant":[67],"downstream":[68],"task.":[69],"Experimental":[70],"findings":[71],"demonstrate":[72],"competitive":[73],"substantial":[77],"enhancements":[78],"ASR":[80],"accuracy":[81],"compared":[82],"alternative":[84],"methods":[85],"situations.":[89],"proposed":[91],"offers":[93],"promising":[94],"advancements":[95],"addressing":[97],"the":[98],"challenges":[99],"posed":[100],"by":[101],"conditions":[104],"applications.":[108]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}