{"id":"https://openalex.org/W4408352359","doi":"https://doi.org/10.1109/icassp49660.2025.10888825","title":"Automatic Detection of Domain Shifts in Speech Enhancement Systems Using Confidence-Based Metrics","display_name":"Automatic Detection of Domain Shifts in Speech Enhancement Systems Using Confidence-Based Metrics","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352359","doi":"https://doi.org/10.1109/icassp49660.2025.10888825"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5116594326","display_name":"Lior Frankel","orcid":null},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Lior Frankel","raw_affiliation_strings":["OriginAI and Bar-Ilan Univerity,Israel"],"affiliations":[{"raw_affiliation_string":"OriginAI and Bar-Ilan Univerity,Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080213609","display_name":"Shlomo E. Chazan","orcid":"https://orcid.org/0000-0002-6614-6112"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Shlomo E. Chazan","raw_affiliation_strings":["OriginAI and Bar-Ilan Univerity,Israel"],"affiliations":[{"raw_affiliation_string":"OriginAI and Bar-Ilan Univerity,Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005409420","display_name":"Jacob Goldberger","orcid":"https://orcid.org/0000-0002-2225-1914"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jacob Goldberger","raw_affiliation_strings":["Bar-Ilan University,Israel"],"affiliations":[{"raw_affiliation_string":"Bar-Ilan University,Israel","institution_ids":["https://openalex.org/I13955877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5116594326"],"corresponding_institution_ids":["https://openalex.org/I13955877"],"apc_list":null,"apc_paid":null,"fwci":1.536,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77953693,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9948999881744385,"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":0.9948999881744385,"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":0.9743000268936157,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9487000107765198,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7004605531692505},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5692599415779114},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5240514278411865},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46242278814315796},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4514445960521698},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37970495223999023},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.35653024911880493},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3457808792591095},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13305923342704773},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.08747050166130066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7004605531692505},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5692599415779114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5240514278411865},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46242278814315796},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4514445960521698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37970495223999023},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.35653024911880493},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3457808792591095},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13305923342704773},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.08747050166130066},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":23,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1901129140","https://openalex.org/W2141998673","https://openalex.org/W2766672686","https://openalex.org/W2962866211","https://openalex.org/W2963341071","https://openalex.org/W2964058413","https://openalex.org/W2972541922","https://openalex.org/W2973220283","https://openalex.org/W3097906045","https://openalex.org/W3097945073","https://openalex.org/W3136499730","https://openalex.org/W3161950572","https://openalex.org/W3198102247","https://openalex.org/W4225302959","https://openalex.org/W4292969786","https://openalex.org/W4311167834","https://openalex.org/W4391164125","https://openalex.org/W6637618735","https://openalex.org/W6688816777","https://openalex.org/W6757632829","https://openalex.org/W6803559545"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2120771489","https://openalex.org/W2904739811","https://openalex.org/W2051376034","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Introducing":[0],"a":[1,6,13,28,54,61,72,91],"domain":[2,29,42,55,62,92],"shift,":[3],"such":[4],"as":[5],"change":[7],"in":[8],"language":[9],"or":[10,40],"environment,":[11],"to":[12],"well-trained":[14],"speech":[15],"enhancement":[16],"system":[17],"can":[18,88],"cause":[19],"severe":[20],"performance":[21],"degradation.":[22],"Most":[23],"current":[24],"research":[25],"assumes":[26],"that":[27,74,85],"shift":[30,56,63],"has":[31,57],"already":[32],"been":[33],"detected":[34],"and":[35,97],"focuses":[36],"on":[37,67],"either":[38],"supervised":[39],"unsupervised":[41],"adaptation":[43],"techniques.":[44],"Here,":[45],"we":[46],"address":[47],"the":[48,69,76,95],"problem":[49],"of":[50,71,78],"automatically":[51],"detecting":[52],"when":[53],"occurred.":[58],"We":[59],"present":[60],"detection":[64],"method":[65,87],"based":[66],"monitoring":[68],"confidence":[70],"network":[73],"predicts":[75],"quality":[77],"enhanced":[79],"speech.":[80],"The":[81],"experimental":[82],"results":[83],"show":[84],"our":[86],"effectively":[89],"detect":[90],"mismatch":[93],"between":[94],"training":[96],"test":[98],"sets.":[99]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-01T08:55:55.761014","created_date":"2025-10-10T00:00:00"}