{"id":"https://openalex.org/W4372346224","doi":"https://doi.org/10.1109/icassp49357.2023.10097114","title":"Half-Temporal and Half-Frequency Attention U<sup>2</sup>Net for Speech Signal Improvement","display_name":"Half-Temporal and Half-Frequency Attention U<sup>2</sup>Net for Speech Signal Improvement","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372346224","doi":"https://doi.org/10.1109/icassp49357.2023.10097114"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5090668921","display_name":"Zehua Zhang","orcid":"https://orcid.org/0000-0003-3215-5317"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zehua Zhang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China","Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101885098","display_name":"Shiyun Xu","orcid":"https://orcid.org/0000-0002-3278-5151"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyun Xu","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China","Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044255594","display_name":"Xuyi Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuyi Zhuang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China","Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073118994","display_name":"Yukun Qian","orcid":"https://orcid.org/0000-0001-9095-4024"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"YuKun Qian","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China","Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041945581","display_name":"Lianyu Zhou","orcid":"https://orcid.org/0000-0001-8212-0839"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianyu Zhou","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China","Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009651653","display_name":"Mingjiang Wang","orcid":"https://orcid.org/0000-0002-4706-009X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjiang Wang","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen),Shenzhen,China","Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen),Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5090668921"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.8133,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70125806,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987000226974487,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/speech-recognition","display_name":"Speech recognition","score":0.747614324092865},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.7252610921859741},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6738832592964172},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6426136493682861},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5714924335479736},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4780728816986084},{"id":"https://openalex.org/keywords/loudness","display_name":"Loudness","score":0.43791621923446655},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.31227147579193115},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.24570098519325256},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21454498171806335},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1170174777507782}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.747614324092865},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7252610921859741},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6738832592964172},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6426136493682861},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5714924335479736},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4780728816986084},{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.43791621923446655},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.31227147579193115},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.24570098519325256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21454498171806335},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1170174777507782},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2884585870","https://openalex.org/W4224931234","https://openalex.org/W4225302959","https://openalex.org/W4225323964","https://openalex.org/W4225905067","https://openalex.org/W4401610398","https://openalex.org/W6753412334","https://openalex.org/W6850335419"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W4200562864","https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121"],"abstract_inverted_index":{"During":[0],"communication,":[1],"volume":[2],"changes,":[3],"noise,":[4,92],"and":[5,15,53,77,87,95,117],"reverberation":[6],"can":[7],"disturb":[8],"speech":[9,45,64],"signals,":[10],"significantly":[11],"affecting":[12],"the":[13,20,23,30,42,71,75,99,110],"quality":[14,43],"intelligibility":[16],"of":[17,22,44],"speech.":[18],"In":[19],"context":[21],"ICASSP":[24],"2023":[25],"Signal":[26,33],"Processing":[27],"Grand":[28,35],"Challenge,":[29],"first":[31],"Speech":[32],"Improvement":[34],"Challenge":[36],"(SIG)":[37],"is":[38,68],"organized":[39],"to":[40],"improve":[41],"signals":[46],"during":[47],"communication.":[48],"This":[49],"paper":[50],"proposes":[51],"half-temporal":[52],"half-frequency":[54],"attention":[55,67],"U":[56],"<sup":[57],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[58],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[59],"Net":[60],"for":[61,70],"improving":[62],"full-band":[63],"signal.":[65],"Channel-spectrum":[66],"proposed":[69,80,104],"skip":[72],"connection":[73],"between":[74],"encoder":[76],"decoder.":[78],"The":[79,103],"model":[81,105],"achieves":[82],"0.353,":[83],"1.289,":[84],"0.604,":[85],"0.625,":[86],"0.924":[88],"improvements":[89],"in":[90,98,109],"signal,":[91],"overall,":[93],"reverberation,":[94],"loudness,":[96],"respectively,":[97],"SIG":[100,111],"subjective":[101],"test.":[102],"achieved":[106],"fourth":[107],"place":[108],"real-time":[112],"track,":[113],"showing":[114],"excellent":[115],"denoising":[116],"de-reverberation":[118],"performance.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}