{"id":"https://openalex.org/W4392902992","doi":"https://doi.org/10.1109/icassp48485.2024.10447832","title":"SMMA-Net: An Audio Clue-Based Target Speaker Extraction Network with Spectrogram Matching and Mutual Attention","display_name":"SMMA-Net: An Audio Clue-Based Target Speaker Extraction Network with Spectrogram Matching and Mutual Attention","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902992","doi":"https://doi.org/10.1109/icassp48485.2024.10447832"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447832","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":"conference-paper","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/A5042363663","display_name":"Ying Hu","orcid":"https://orcid.org/0000-0001-7505-1767"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Hu","raw_affiliation_strings":["Key Laboratory of Signal Detection and Processing,Xinjiang, Urumqi,China","Key Laboratory of Signal Detection and Processing, Xinjiang, Urumqi, China","School of Computer Science and Technology, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Signal Detection and Processing,Xinjiang, Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Key Laboratory of Signal Detection and Processing, Xinjiang, Urumqi, China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103460101","display_name":"Haitao Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitao Xu","raw_affiliation_strings":["Key Laboratory of Signal Detection and Processing,Xinjiang, Urumqi,China","Key Laboratory of Signal Detection and Processing, Xinjiang, Urumqi, China","School of Computer Science and Technology, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Signal Detection and Processing,Xinjiang, Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Key Laboratory of Signal Detection and Processing, Xinjiang, Urumqi, China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100881617","display_name":"Zhongcun Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100005","display_name":"Silicon Technologies (United States)","ror":"https://ror.org/013qwzt07","country_code":"US","type":"company","lineage":["https://openalex.org/I4210100005"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhongcun Guo","raw_affiliation_strings":["HiSilicon Technologies Co., Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HiSilicon Technologies Co., Limited","institution_ids":["https://openalex.org/I4210100005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024772368","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0001-6604-0951"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["Key Laboratory of Signal Detection and Processing,Xinjiang, Urumqi,China","Key Laboratory of Signal Detection and Processing, Xinjiang, Urumqi, China","School of Computer Science and Technology, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Signal Detection and Processing,Xinjiang, Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Key Laboratory of Signal Detection and Processing, Xinjiang, Urumqi, China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100317921","display_name":"Liang He","orcid":"https://orcid.org/0000-0003-4826-629X"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China","Department of Electronic Engineering, Tsinghua University, Beijing, China","School of Computer Science and Technology, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3372,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.93120016,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1496","last_page":"1500"},"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":0.9998000264167786,"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":0.9997000098228455,"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/spectrogram","display_name":"Spectrogram","score":0.9224209785461426},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7795789241790771},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7006738185882568},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5482542514801025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47758081555366516},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44607287645339966},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.443278431892395},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.436400830745697},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4333247244358063},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4312889575958252},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4231805205345154},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4160420596599579},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13243460655212402},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09905776381492615}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9224209785461426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7795789241790771},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7006738185882568},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5482542514801025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47758081555366516},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44607287645339966},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.443278431892395},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.436400830745697},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4333247244358063},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4312889575958252},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4231805205345154},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4160420596599579},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13243460655212402},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09905776381492615},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447832","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W840431159","https://openalex.org/W2079362249","https://openalex.org/W2082183045","https://openalex.org/W2150415460","https://openalex.org/W2951130829","https://openalex.org/W2973062255","https://openalex.org/W2981609437","https://openalex.org/W3016361963","https://openalex.org/W3035414587","https://openalex.org/W3097653961","https://openalex.org/W3103434036","https://openalex.org/W3160464260","https://openalex.org/W3162534564","https://openalex.org/W3163652268","https://openalex.org/W3198234746","https://openalex.org/W4200634403","https://openalex.org/W4224918929","https://openalex.org/W4247773827","https://openalex.org/W4283803134","https://openalex.org/W4288054834","https://openalex.org/W4367597591","https://openalex.org/W4372259900","https://openalex.org/W4372260086","https://openalex.org/W4372271325","https://openalex.org/W4372271367","https://openalex.org/W4385245566","https://openalex.org/W4385346076","https://openalex.org/W4385823161","https://openalex.org/W4385823352","https://openalex.org/W4386047745","https://openalex.org/W6730039835","https://openalex.org/W6793164127","https://openalex.org/W6809698605","https://openalex.org/W6844662008"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2997457842","https://openalex.org/W1997431798"],"abstract_inverted_index":{"We":[0,37],"propose":[1],"a":[2,72],"deep":[3],"neural":[4],"network":[5],"with":[6],"spectrogram":[7,28],"matching":[8,29],"and":[9,32,47,56],"mutual":[10,33],"attention":[11,34],"(SMMA-Net)":[12],"for":[13,94,99],"audio":[14],"clue-based":[15],"target":[16],"speaker":[17,100],"extraction":[18],"(TSE).":[19],"To":[20],"effectively":[21],"use":[22],"the":[23,42,51,68,79,90,104],"auxiliary":[24],"speech,":[25],"we":[26],"proposed":[27,65],"(SM)":[30],"strategy":[31,55],"(MA)":[35],"block.":[36,58],"conducted":[38],"all":[39],"experiments":[40],"on":[41,78],"WSJ0-2mix-extr":[43],"dataset.":[44],"The":[45,59,107],"ablation":[46],"comparison":[48],"studies":[49],"verified":[50],"effectiveness":[52],"of":[53,75,81,92],"SM":[54],"MA":[57],"experimental":[60],"results":[61],"show":[62],"that":[63,89,98],"our":[64],"method":[66],"outperforms":[67],"state-of-the-art":[69],"methods":[70],"by":[71],"sizable":[73],"margin":[74],"1.3":[76],"dB":[77],"metric":[80],"scale-invariant":[82],"signal-to-distortion":[83],"ratio":[84],"improvement.":[85],"Additionally,":[86],"SMMA-Net":[87],"achieved":[88],"performance":[91],"model":[93],"TSE":[95],"task":[96,102],"exceeds":[97],"separation":[101],"under":[103],"similar":[105],"architecture.":[106],"main":[108],"code":[109],"will":[110],"be":[111],"available":[112],"at":[113],"https://github.com/Ht-Xu/SMMA-Net.":[114]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}