{"id":"https://openalex.org/W4372341576","doi":"https://doi.org/10.1109/icassp49357.2023.10096467","title":"Hybridformer: Improving Squeezeformer with Hybrid Attention and NSR Mechanism","display_name":"Hybridformer: Improving Squeezeformer with Hybrid Attention and NSR Mechanism","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372341576","doi":"https://doi.org/10.1109/icassp49357.2023.10096467"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096467","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/A5101516876","display_name":"Yuguang Yang","orcid":"https://orcid.org/0009-0003-3892-0523"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuguang Yang","raw_affiliation_strings":["Ximalaya Inc,ShangHai,China","Ximalaya Inc, ShangHai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ximalaya Inc,ShangHai,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc, ShangHai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100665153","display_name":"Pan Yu","orcid":"https://orcid.org/0000-0002-3333-9719"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yu Pan","raw_affiliation_strings":["University of Alberta,Edmonton,Canada","University of Alberta, Edmonton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta,Edmonton,Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100654943","display_name":"Jingjing Yin","orcid":"https://orcid.org/0000-0002-4400-9897"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingjing Yin","raw_affiliation_strings":["Ximalaya Inc,ShangHai,China","Ximalaya Inc, ShangHai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ximalaya Inc,ShangHai,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc, ShangHai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090367911","display_name":"Jiangyu Han","orcid":"https://orcid.org/0000-0001-5390-8520"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiangyu Han","raw_affiliation_strings":["Ximalaya Inc,ShangHai,China","Ximalaya Inc, ShangHai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ximalaya Inc,ShangHai,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc, ShangHai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101468661","display_name":"Lei Ma","orcid":"https://orcid.org/0000-0002-8621-2420"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Lei Ma","raw_affiliation_strings":["University of Alberta,Edmonton,Canada","University of Alberta, Edmonton, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta,Edmonton,Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100618443","display_name":"Heng Lu","orcid":"https://orcid.org/0009-0009-9236-8825"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heng Lu","raw_affiliation_strings":["Ximalaya Inc,ShangHai,China","Ximalaya Inc, ShangHai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ximalaya Inc,ShangHai,China","institution_ids":[]},{"raw_affiliation_string":"Ximalaya Inc, ShangHai, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6526,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7389166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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/softmax-function","display_name":"Softmax function","score":0.7580739855766296},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7389033436775208},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7049329280853271},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5519649982452393},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5137232542037964},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4961563050746918},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4646083414554596},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4537546634674072},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4166805148124695},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3762929439544678},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36554205417633057},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3590317964553833},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12949249148368835}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.7580739855766296},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7389033436775208},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7049329280853271},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5519649982452393},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5137232542037964},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4961563050746918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4646083414554596},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4537546634674072},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4166805148124695},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3762929439544678},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36554205417633057},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3590317964553833},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12949249148368835},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096467","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":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1586532344","https://openalex.org/W2127141656","https://openalex.org/W2936774411","https://openalex.org/W2951104886","https://openalex.org/W2963250244","https://openalex.org/W2973215447","https://openalex.org/W3015457435","https://openalex.org/W3015537910","https://openalex.org/W3016010032","https://openalex.org/W3033529678","https://openalex.org/W3097777922","https://openalex.org/W3141854550","https://openalex.org/W3155806510","https://openalex.org/W3163842642","https://openalex.org/W3167976421","https://openalex.org/W4225292962","https://openalex.org/W4225525539","https://openalex.org/W4226191785","https://openalex.org/W4281779489","https://openalex.org/W4283067311","https://openalex.org/W4287667694","https://openalex.org/W4288277460","https://openalex.org/W4309793872","https://openalex.org/W4385245566","https://openalex.org/W6635078382","https://openalex.org/W6739901393","https://openalex.org/W6752515464","https://openalex.org/W6766844300","https://openalex.org/W6779163297","https://openalex.org/W6783267081","https://openalex.org/W6783944145","https://openalex.org/W6792376965","https://openalex.org/W6793987055","https://openalex.org/W6810370753","https://openalex.org/W6838276489"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W4226420367","https://openalex.org/W2980176872","https://openalex.org/W2962876041","https://openalex.org/W3090555870","https://openalex.org/W3108503355","https://openalex.org/W2249953602","https://openalex.org/W2801655600","https://openalex.org/W2944691285"],"abstract_inverted_index":{"SqueezeFormer":[0,37,51,127],"has":[1],"recently":[2],"shown":[3],"impressive":[4],"performance":[5],"in":[6,52],"automatic":[7],"speech":[8,135],"recognition":[9],"(ASR).":[10],"However,":[11],"its":[12],"inference":[13,75,144],"speed":[14,145],"suffers":[15],"from":[16],"the":[17,27,32,73,95,98,108,129,138,142],"quadratic":[18],"complexity":[19],"of":[20,36,97],"softmax-attention":[21],"(SA).":[22],"In":[23,40],"addition,":[24],"limited":[25],"by":[26],"large":[28],"convolution":[29],"kernel":[30],"size,":[31],"local":[33,102],"modeling":[34],"ability":[35,96],"is":[38,91,136,152],"insufficient.":[39],"this":[41],"paper,":[42],"we":[43,59],"propose":[44,66],"a":[45,53,67,78,118],"novel":[46],"method":[47],"HybridFormer":[48,115,139],"to":[49,71,93,100,147],"improve":[50,141],"fast":[54],"and":[55,65],"efficient":[56],"way.":[57],"Specifically,":[58],"first":[60],"incorporate":[61],"linear":[62],"attention":[63],"(LA)":[64],"hybrid":[68,79],"LASA":[69],"paradigm":[70],"increase":[72],"model\u2019s":[74,143],"speed.":[76],"Second,":[77],"neural":[80],"architecture":[81],"search":[82],"(NAS)":[83],"guided":[84],"structural":[85],"re-parameterization":[86],"(SRep)":[87],"mechanism,":[88],"termed":[89],"NSR,":[90],"proposed":[92,114],"enhance":[94],"model":[99],"extract":[101],"interactions.":[103],"Extensive":[104],"experiments":[105],"conducted":[106],"on":[107,128],"LibriSpeech":[109],"dataset":[110],"demonstrate":[111],"that":[112],"our":[113],"can":[116,140],"achieve":[117],"9.1%":[119],"relative":[120],"word":[121],"error":[122],"rate":[123],"(WER)":[124],"reduction":[125],"over":[126],"test-other":[130],"dataset.":[131],"Furthermore,":[132],"when":[133],"input":[134],"30s,":[137],"up":[146],"18%.":[148],"Our":[149],"source":[150],"code":[151],"available":[153],"online":[154],"<sup":[155],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[156],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[157],".":[158]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}