{"id":"https://openalex.org/W4392904056","doi":"https://doi.org/10.1109/icassp48485.2024.10445853","title":"SPATIALCODEC: Neural Spatial Speech Coding","display_name":"SPATIALCODEC: Neural Spatial Speech Coding","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904056","doi":"https://doi.org/10.1109/icassp48485.2024.10445853"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445853","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10445853","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5069215134","display_name":"Zhongweiyang Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhongweiyang Xu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100577133","display_name":"Yong Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Xu","raw_affiliation_strings":["Tencent AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047630225","display_name":"Vinay Kothapally","orcid":"https://orcid.org/0000-0002-2111-3333"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Vinay Kothapally","raw_affiliation_strings":["Tencent AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101497068","display_name":"Heming Wang","orcid":"https://orcid.org/0000-0003-3057-9060"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heming Wang","raw_affiliation_strings":["The Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012381843","display_name":"Muqiao Yang","orcid":"https://orcid.org/0000-0001-6273-0138"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muqiao Yang","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"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/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"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":0.02697546,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1131","last_page":"1135"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.8697705268859863},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6817234754562378},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5397433042526245},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.522418737411499},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5134001970291138},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.49177172780036926},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.4890783429145813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4723718464374542},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.462738573551178},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4573800265789032},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4401237964630127},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4240376651287079},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42263680696487427},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.42172276973724365},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33326053619384766},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.30703407526016235},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1726120114326477},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14714261889457703}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8697705268859863},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6817234754562378},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5397433042526245},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.522418737411499},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5134001970291138},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.49177172780036926},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.4890783429145813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4723718464374542},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.462738573551178},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4573800265789032},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4401237964630127},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4240376651287079},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42263680696487427},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.42172276973724365},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33326053619384766},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30703407526016235},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1726120114326477},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14714261889457703},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445853","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10445853","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W316027304","https://openalex.org/W1481955708","https://openalex.org/W1634005169","https://openalex.org/W2089473323","https://openalex.org/W2091248202","https://openalex.org/W2113638573","https://openalex.org/W2117497587","https://openalex.org/W2141532435","https://openalex.org/W2151626637","https://openalex.org/W2292235217","https://openalex.org/W2486063739","https://openalex.org/W2752796333","https://openalex.org/W2763188033","https://openalex.org/W2807002113","https://openalex.org/W2889048668","https://openalex.org/W2963799213","https://openalex.org/W2970006822","https://openalex.org/W2974407961","https://openalex.org/W3092028330","https://openalex.org/W3101330598","https://openalex.org/W3127838239","https://openalex.org/W3140429000","https://openalex.org/W3215615641","https://openalex.org/W4225302959","https://openalex.org/W4281570978","https://openalex.org/W4297752165","https://openalex.org/W4307323391","https://openalex.org/W4313679638","https://openalex.org/W4372270198","https://openalex.org/W4372279529","https://openalex.org/W4377231659","https://openalex.org/W4380136719","https://openalex.org/W4385989146","https://openalex.org/W6630442970","https://openalex.org/W6696768431","https://openalex.org/W6754473786","https://openalex.org/W6767111847","https://openalex.org/W6783867762","https://openalex.org/W6810523761","https://openalex.org/W6848735303","https://openalex.org/W6852581948","https://openalex.org/W6853096648"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W2129913000","https://openalex.org/W2374470469","https://openalex.org/W2352448339","https://openalex.org/W2787189739","https://openalex.org/W2899318368","https://openalex.org/W3095556352","https://openalex.org/W2159899134","https://openalex.org/W2363660481"],"abstract_inverted_index":{"In":[0,92],"this":[1],"work,":[2],"we":[3,94],"address":[4],"the":[5,20,69,89,102],"challenge":[6],"of":[7,22],"encoding":[8],"speech":[9],"captured":[10],"by":[11],"a":[12,36,44,61,78,114],"microphone":[13],"array":[14],"using":[15],"deep":[16],"learning":[17],"techniques":[18],"with":[19,72,130],"aim":[21],"preserving":[23],"and":[24,53,76,118,134,144],"accurately":[25],"reconstructing":[26],"crucial":[27],"spatial":[28,38,82,103,107,127],"cues":[29],"embedded":[30],"in":[31],"multi-channel":[32,86],"recordings.":[33],"We":[34],"propose":[35,96],"neural":[37,50,62,136],"audio":[39,121],"coding":[40],"framework":[41],"that":[42],"achieves":[43],"high":[45,131],"compression":[46],"ratio,":[47],"leveraging":[48],"single-channel":[49],"sub-band":[51,63],"codec":[52,64],"SpatialCodec.":[54],"Our":[55,123],"approach":[56],"encompasses":[57],"two":[58],"phases:":[59],"(i)":[60,106],"is":[65],"designed":[66],"to":[67,100],"encode":[68],"reference":[70],"channel":[71],"low":[73],"bit":[74],"rates,":[75],"(ii),":[77,119],"SpatialCodec":[79],"captures":[80],"relative":[81],"information":[83],"for":[84],"accurate":[85],"reconstruction":[87],"at":[88,141,148],"decoder":[90],"end.":[91],"addition,":[93],"also":[95],"novel":[97],"evaluation":[98],"metrics":[99],"assess":[101],"cue":[104],"preservation:":[105],"similarity,":[108],"which":[109],"calculates":[110],"cosine":[111],"similarity":[112],"on":[113],"spatially":[115],"intuitive":[116],"beamspace,":[117],"beamformed":[120],"quality.":[122],"system":[124],"shows":[125],"superior":[126],"performance":[128],"compared":[129],"bitrate":[132],"baselines":[133],"black-box":[135],"architecture.":[137],"Demos":[138],"are":[139,146],"available":[140,147],"https://xzwy.github.io/SpatialCodecDemo.":[142],"Codes":[143],"models":[145],"https://github.com/XZWY/SpatialCodec.":[149]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}