{"id":"https://openalex.org/W4408347294","doi":"https://doi.org/10.1109/icassp49660.2025.10888151","title":"BANC: Towards Efficient Binaural Audio Neural Codec for Overlapping Speech","display_name":"BANC: Towards Efficient Binaural Audio Neural Codec for Overlapping Speech","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408347294","doi":"https://doi.org/10.1109/icassp49660.2025.10888151"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888151","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888151","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/A5063105649","display_name":"Anton Ratnarajah","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anton Ratnarajah","raw_affiliation_strings":["University of Maryland,College Park,MD,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,MD,USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101785327","display_name":"Shi-Xiong Zhang","orcid":"https://orcid.org/0009-0007-7803-2407"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shi-Xiong Zhang","raw_affiliation_strings":["Tencent AI Lab,Bellevue,WA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Bellevue,WA,USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab,Bellevue,WA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Bellevue,WA,USA","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03627545,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.9995999932289124,"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":0.9995999932289124,"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":0.9926999807357788,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.986299991607666,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.8695147037506104},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7894651889801025},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7026249170303345},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.6584475040435791},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.5907323956489563},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5428604483604431},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3195183277130127},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.26291003823280334},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15995416045188904}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.8695147037506104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7894651889801025},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7026249170303345},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.6584475040435791},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.5907323956489563},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5428604483604431},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3195183277130127},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.26291003823280334},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15995416045188904}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888151","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888151","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":28,"referenced_works":["https://openalex.org/W1498609987","https://openalex.org/W2046317813","https://openalex.org/W2067295501","https://openalex.org/W2097645910","https://openalex.org/W2108532241","https://openalex.org/W2752796333","https://openalex.org/W2952218014","https://openalex.org/W2960533729","https://openalex.org/W2963208781","https://openalex.org/W3015279216","https://openalex.org/W3016003977","https://openalex.org/W3096468295","https://openalex.org/W3178031393","https://openalex.org/W3198454118","https://openalex.org/W3206257526","https://openalex.org/W3215615641","https://openalex.org/W4226373941","https://openalex.org/W4281264304","https://openalex.org/W4307323391","https://openalex.org/W4312337341","https://openalex.org/W4372270198","https://openalex.org/W4372341113","https://openalex.org/W6639363673","https://openalex.org/W6655322045","https://openalex.org/W6744762798","https://openalex.org/W6772349387","https://openalex.org/W6783867762","https://openalex.org/W6852581948"],"related_works":["https://openalex.org/W4252424250","https://openalex.org/W2374470469","https://openalex.org/W2129913000","https://openalex.org/W2899318368","https://openalex.org/W2363660481","https://openalex.org/W2352448339","https://openalex.org/W2159899134","https://openalex.org/W2787189739","https://openalex.org/W3095556352","https://openalex.org/W1999835922"],"abstract_inverted_index":{"We":[0],"introduce":[1],"BANC,":[2],"a":[3],"neural":[4],"binaural":[5,78,86],"audio":[6],"codec":[7],"designed":[8],"for":[9,76],"efficient":[10],"speech":[11,52,79,93,107],"compression":[12],"in":[13,71],"single":[14],"and":[15,42,54,97,108],"two-speaker":[16],"scenarios":[17],"while":[18],"preserving":[19],"the":[20,59,73,102],"spatial":[21,55,64,109],"location":[22],"information":[23],"of":[24,36,61,104],"each":[25,62],"speaker.":[26],"Our":[27],"key":[28],"contributions":[29],"are":[30],"as":[31],"follows:":[32],"1)":[33],"The":[34],"ability":[35],"our":[37,89],"proposed":[38],"model":[39],"to":[40,83,100],"compress":[41],"decode":[43],"overlapping":[44],"speech.":[45],"2)":[46],"A":[47],"novel":[48],"architecture":[49],"that":[50],"compresses":[51],"content":[53],"cues":[56],"separately,":[57],"ensuring":[58],"preservation":[60],"speaker\u2019s":[63],"context":[65],"after":[66],"decoding.":[67],"3)":[68],"BANC\u2019s":[69,105],"proficiency":[70],"reducing":[72],"bandwidth":[74],"required":[75],"compressing":[77,84],"by":[80],"48%":[81],"compared":[82],"individual":[85],"channels.":[87],"In":[88],"evaluation,":[90],"we":[91],"employed":[92],"enhancement,":[94],"room":[95],"acoustics,":[96],"perceptual":[98],"metrics":[99],"assess":[101],"accuracy":[103],"clean":[106],"cue":[110],"estimates.":[111]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}