{"id":"https://openalex.org/W4391307238","doi":"https://doi.org/10.1109/icspcc59353.2023.10400283","title":"Convolutional Recurrent Neural Network with Attention for 3D Speech Enhancement","display_name":"Convolutional Recurrent Neural Network with Attention for 3D Speech Enhancement","publication_year":2023,"publication_date":"2023-11-14","ids":{"openalex":"https://openalex.org/W4391307238","doi":"https://doi.org/10.1109/icspcc59353.2023.10400283"},"language":"en","primary_location":{"id":"doi:10.1109/icspcc59353.2023.10400283","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icspcc59353.2023.10400283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","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/A5113113933","display_name":"Han Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Han Yin","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027263923","display_name":"Jisheng Bai","orcid":"https://orcid.org/0000-0002-9803-8212"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jisheng Bai","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103175728","display_name":"Mou Wang","orcid":"https://orcid.org/0000-0002-6476-2501"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mou Wang","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056584987","display_name":"Siwei Huang","orcid":"https://orcid.org/0000-0001-8409-1330"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siwei Huang","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101934534","display_name":"Yafei Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yafei Jia","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065376714","display_name":"Jianfeng Chen","orcid":"https://orcid.org/0000-0002-7281-7138"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Chen","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University,Joint Laboratory of Environmental Sound Sensing,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5113113933"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.2033,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.49896727,"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":"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":0.9961000084877014,"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":0.9961000084877014,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7628903388977051},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6960349678993225},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6089969873428345},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6080145835876465},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4698046147823334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3839627206325531},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.28280800580978394},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.04984396696090698}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7628903388977051},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6960349678993225},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6089969873428345},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6080145835876465},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4698046147823334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3839627206325531},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28280800580978394},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.04984396696090698}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icspcc59353.2023.10400283","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icspcc59353.2023.10400283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","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":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1677182931","https://openalex.org/W1920741591","https://openalex.org/W1975301756","https://openalex.org/W2061678360","https://openalex.org/W2078528584","https://openalex.org/W2102950268","https://openalex.org/W2110322414","https://openalex.org/W2112469598","https://openalex.org/W2405774341","https://openalex.org/W2605589342","https://openalex.org/W2759976799","https://openalex.org/W2924149053","https://openalex.org/W2943554574","https://openalex.org/W2990594533","https://openalex.org/W3004309045","https://openalex.org/W3015199127","https://openalex.org/W3088775906","https://openalex.org/W3094253649","https://openalex.org/W3096408984","https://openalex.org/W3096641561","https://openalex.org/W3160973314","https://openalex.org/W3211408542","https://openalex.org/W3213747130","https://openalex.org/W4205689591","https://openalex.org/W4250482878","https://openalex.org/W4372260406"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W2578422401","https://openalex.org/W2770665941","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853","https://openalex.org/W197907117"],"abstract_inverted_index":{"3D":[0],"speech":[1,21],"enhancement":[2,22],"can":[3],"effectively":[4],"improve":[5],"the":[6,43,53,66,83,86,98,102],"auditory":[7],"experience":[8],"and":[9,55,71,88],"plays":[10],"a":[11,36,77],"crucial":[12],"role":[13],"in":[14,26,51,85],"augmented":[15],"reality":[16],"technology.":[17],"However,":[18],"traditional":[19],"convolutional-based":[20],"methods":[23],"have":[24],"limitations":[25],"extracting":[27],"dynamic":[28,48],"voice":[29],"information.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34,75],"incorporate":[35],"dual-path":[37],"recurrent":[38],"neural":[39],"network":[40,84],"block":[41],"into":[42],"U-Net":[44],"to":[45,64,80],"iteratively":[46],"extract":[47],"audio":[49],"information":[50],"both":[52],"time":[54,89],"frequency":[56],"domains.":[57,90],"And":[58],"an":[59],"attention":[60],"mechanism":[61],"is":[62],"proposed":[63],"fuse":[65],"original":[67],"signal,":[68,70],"reference":[69],"generated":[72],"masks.":[73],"Moreover,":[74],"introduce":[76],"loss":[78],"function":[79],"simultaneously":[81],"optimize":[82],"time-frequency":[87],"Experimental":[91],"results":[92],"show":[93],"that":[94],"our":[95],"system":[96],"outperforms":[97],"state-of-the-art":[99],"systems":[100],"on":[101],"dataset":[103],"of":[104],"ICASSP":[105],"L3DAS23":[106],"challenge.":[107]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}