{"id":"https://openalex.org/W4415433538","doi":"https://doi.org/10.21437/interspeech.2025-800","title":"CabinSep: IR-Augmented Mask-Based MVDR for Real-Time In-car Speech Separation with Distributed Heterogeneous Arrays","display_name":"CabinSep: IR-Augmented Mask-Based MVDR for Real-Time In-car Speech Separation with Distributed Heterogeneous Arrays","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433538","doi":"https://doi.org/10.21437/interspeech.2025-800"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-800","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","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/A5091225905","display_name":"Runduo Han","orcid":"https://orcid.org/0009-0009-4380-4424"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Runduo Han","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101330960","display_name":"Yanxin Hu","orcid":"https://orcid.org/0009-0009-4388-8883"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanxin Hu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072957681","display_name":"Yanan Fu","orcid":"https://orcid.org/0000-0003-3332-8216"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yihui Fu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100410545","display_name":"Zihan Zhang","orcid":"https://orcid.org/0000-0002-0415-7721"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zihan Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031232410","display_name":"Yukai Jv","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yukai Jv","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379216","display_name":"Li Chen","orcid":"https://orcid.org/0000-0002-1754-0607"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5091225905"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40266625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4978","last_page":"4982"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9970999956130981,"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":0.9970999956130981,"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":0.9757999777793884,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9657999873161316,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/separation","display_name":"Separation (statistics)","score":0.3497999906539917},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.28200000524520874},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.27309998869895935},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.26919999718666077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.578000009059906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4325000047683716},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.28290000557899475},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.28200000524520874},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2791999876499176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2745000123977661},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.26919999718666077},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26820001006126404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2025-800","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}