{"id":"https://openalex.org/W4416799154","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249243","title":"Multi-Stage Speech Enhancement with Cascaded SNR Domain Shifts","display_name":"Multi-Stage Speech Enhancement with Cascaded SNR Domain Shifts","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799154","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249243"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5100697545","display_name":"Xiaoran Li","orcid":"https://orcid.org/0000-0002-7438-8920"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoran Li","raw_affiliation_strings":["University of Science and Technology of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089001438","display_name":"Zilu Guo","orcid":"https://orcid.org/0009-0000-0486-6088"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zilu Guo","raw_affiliation_strings":["University of Science and Technology of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101081618","display_name":"Jun Du","orcid":"https://orcid.org/0000-0001-8576-1041"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38650585,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1039","last_page":"1044"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9968000054359436,"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":0.9968000054359436,"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":0.00139999995008111,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0003000000142492354,"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/speech-enhancement","display_name":"Speech enhancement","score":0.8048999905586243},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.46470001339912415},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.4203000068664551},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.40950000286102295},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.3718999922275543},{"id":"https://openalex.org/keywords/performance-enhancement","display_name":"Performance enhancement","score":0.3650999963283539},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3495999872684479}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.8048999905586243},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6503000259399414},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5166000127792358},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.503000020980835},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.46470001339912415},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.4203000068664551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4169999957084656},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.40950000286102295},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C2986800882","wikidata":"https://www.wikidata.org/wiki/Q7168187","display_name":"Performance enhancement","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.28760001063346863},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2069681747","https://openalex.org/W2070126272","https://openalex.org/W2141998673","https://openalex.org/W2516547830","https://openalex.org/W2889442120","https://openalex.org/W2891433113","https://openalex.org/W2998832642","https://openalex.org/W3015338123","https://openalex.org/W3015526955","https://openalex.org/W3016447038","https://openalex.org/W3030895838","https://openalex.org/W3096408984","https://openalex.org/W3097312999","https://openalex.org/W3097906045","https://openalex.org/W3160085755","https://openalex.org/W3198680319","https://openalex.org/W3205770165","https://openalex.org/W3213188934","https://openalex.org/W4221144097","https://openalex.org/W4221162870","https://openalex.org/W4310059968","https://openalex.org/W4372270327","https://openalex.org/W4402112226","https://openalex.org/W4402112483","https://openalex.org/W4402112486"],"related_works":[],"abstract_inverted_index":{"This":[0,93],"paper":[1],"introduces":[2],"a":[3],"novel":[4],"multi-stage":[5,91,101],"speech":[6],"enhancement":[7,20],"(SE)":[8],"algorithm":[9],"that":[10],"leverages":[11],"cascaded":[12],"signal-to-noise":[13],"ratio":[14],"(SNR)":[15],"domain":[16,88],"shifts":[17,89],"to":[18,62],"improve":[19],"performance.":[21],"The":[22],"proposed":[23],"method":[24],"decomposes":[25],"the":[26,40,55,84],"SE":[27,102],"task":[28],"into":[29,98],"multiple":[30],"stages,":[31],"where":[32],"each":[33],"stage's":[34,42],"output":[35],"SNR":[36,49,60,66,87],"is":[37],"optimized":[38],"for":[39],"next":[41],"input.":[43],"By":[44],"training":[45],"models":[46],"on":[47,69],"distinct":[48],"domains":[50],"and":[51,71,80],"using":[52],"post-processing":[53],"fusion,":[54],"approach":[56],"effectively":[57],"elevates":[58],"low":[59],"inputs":[61],"higher,":[63],"more":[64],"optimal":[65],"domains.":[67],"Experiments":[68],"CHiME-4":[70],"DNS2020":[72],"datasets":[73],"demonstrate":[74],"significant":[75],"improvements":[76],"in":[77,90],"objective":[78],"intelligibility":[79],"perceptual":[81],"quality,":[82],"showcasing":[83],"effectiveness":[85],"of":[86],"enhancement.":[92],"work":[94],"provides":[95],"new":[96],"insights":[97],"designing":[99],"efficient":[100],"models.":[103]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}