{"id":"https://openalex.org/W4392931424","doi":"https://doi.org/10.1109/icassp48485.2024.10445847","title":"Efficient Multi-Channel Speech Enhancement with Spherical Harmonics Injection for Directional Encoding","display_name":"Efficient Multi-Channel Speech Enhancement with Spherical Harmonics Injection for Directional Encoding","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392931424","doi":"https://doi.org/10.1109/icassp48485.2024.10445847"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445847","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10445847","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/A5023225646","display_name":"Jiahui Pan","orcid":"https://orcid.org/0000-0002-7576-6743"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiahui Pan","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,China","College of Computer Science, Inner Mongolia University, China"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027731526","display_name":"Pengjie Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengjie Shen","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,China","College of Computer Science, Inner Mongolia University, China"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100715414","display_name":"Hui Zhang","orcid":"https://orcid.org/0000-0001-8012-4684"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Zhang","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,China","College of Computer Science, Inner Mongolia University, China"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100693230","display_name":"Xueliang Zhang","orcid":"https://orcid.org/0000-0002-0406-1105"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueliang Zhang","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,China","College of Computer Science, Inner Mongolia University, China"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023225646"],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":0.3768,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.49831343,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"9561","last_page":"9565"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9988999962806702,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7615966796875},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.6820929050445557},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6061440110206604},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5868620872497559},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5499621033668518},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.51726895570755},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.48205623030662537},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42597246170043945},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4211446940898895},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.41024166345596313},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.3946973383426666},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3495529294013977},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16413339972496033},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.10313895344734192},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09940820932388306},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.08749774098396301},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.07175979018211365}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7615966796875},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.6820929050445557},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6061440110206604},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5868620872497559},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5499621033668518},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.51726895570755},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.48205623030662537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42597246170043945},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4211446940898895},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.41024166345596313},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.3946973383426666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3495529294013977},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16413339972496033},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.10313895344734192},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09940820932388306},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.08749774098396301},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.07175979018211365},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445847","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10445847","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":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1974387177","https://openalex.org/W2020637929","https://openalex.org/W2022899627","https://openalex.org/W2045956438","https://openalex.org/W2048541712","https://openalex.org/W2141998673","https://openalex.org/W2146673011","https://openalex.org/W2168729028","https://openalex.org/W2289394825","https://openalex.org/W2327701832","https://openalex.org/W2494085323","https://openalex.org/W2539508298","https://openalex.org/W2937525188","https://openalex.org/W2948042249","https://openalex.org/W2991361823","https://openalex.org/W3004309045","https://openalex.org/W3015081319","https://openalex.org/W3030781580","https://openalex.org/W3105118415","https://openalex.org/W3196940724","https://openalex.org/W3197627016","https://openalex.org/W3198156015","https://openalex.org/W3198511309","https://openalex.org/W4210402803","https://openalex.org/W4226071457","https://openalex.org/W4246924397"],"related_works":["https://openalex.org/W2597829360","https://openalex.org/W4375869169","https://openalex.org/W2402466562","https://openalex.org/W2921661700","https://openalex.org/W2138406058","https://openalex.org/W2153897396","https://openalex.org/W2157102033","https://openalex.org/W3211091508","https://openalex.org/W2131486661","https://openalex.org/W2005805562"],"abstract_inverted_index":{"Multi-channel":[0],"speech":[1,4,26,136],"enhancement":[2,27],"extracts":[3],"using":[5,48],"multiple":[6],"microphones":[7],"that":[8],"capture":[9],"spatial":[10,42,62,94],"cues.":[11],"Effectively":[12],"utilizing":[13],"directional":[14,125],"information":[15],"is":[16,112],"therefore":[17],"key.":[18],"Deep":[19],"learning":[20],"shows":[21],"great":[22],"potential":[23],"on":[24,97],"multi-channel":[25,135],"and":[28,74,102,117],"often":[29],"takes":[30],"short-time":[31],"Fourier":[32],"Transform":[33],"(STFT)":[34],"as":[35,54],"inputs":[36],"directly.":[37],"To":[38],"fully":[39],"leverage":[40],"the":[41,72,77,84,88,131,134],"information,":[43],"we":[44,91],"introduce":[45],"a":[46],"method":[47],"spherical":[49,121],"harmonics":[50,122],"transform":[51],"(SHT)":[52],"coefficients":[53,59],"auxiliary":[55],"model":[56,66,106,128],"inputs.":[57],"These":[58],"concisely":[60],"represent":[61],"distributions.":[63],"Specifically,":[64],"our":[65,105,127],"has":[67],"two":[68],"encoders,":[69],"one":[70],"for":[71,76],"STFT":[73],"another":[75],"SHT.":[78],"By":[79,119],"fusing":[80],"both":[81],"encoders":[82],"in":[83],"decoder":[85],"to":[86,123],"estimate":[87],"enhanced":[89],"STFT,":[90],"effectively":[92],"incorporate":[93,124],"context.":[95],"Evaluations":[96],"TIMIT":[98],"under":[99],"varying":[100],"noise":[101],"reverberation":[103],"show":[104],"outperforms":[107],"established":[108],"benchmarks.":[109],"Remarkably,":[110],"this":[111],"achieved":[113],"with":[114],"fewer":[115],"computations":[116],"parameters.":[118],"leveraging":[120],"cues,":[126],"efficiently":[129],"improves":[130],"performance":[132],"of":[133],"enhancement.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}