{"id":"https://openalex.org/W4408355350","doi":"https://doi.org/10.1109/icassp49660.2025.10887831","title":"Breaking Through the Spike: Spike Window Decoding for Accelerated and Precise Automatic Speech Recognition","display_name":"Breaking Through the Spike: Spike Window Decoding for Accelerated and Precise Automatic Speech Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355350","doi":"https://doi.org/10.1109/icassp49660.2025.10887831"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887831","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5100685146","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0001-9138-0069"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["TRIP.COM GROUP,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"TRIP.COM GROUP,Shanghai,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669567","display_name":"Tianhao Zhang","orcid":"https://orcid.org/0000-0002-6526-7414"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian-Hao Zhang","raw_affiliation_strings":["University of Science and Technology Beijing,School of Computer and Communication Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing,School of Computer and Communication Engineering,Beijing,China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102713104","display_name":"Chao Luo","orcid":"https://orcid.org/0000-0002-0600-5940"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Luo","raw_affiliation_strings":["TRIP.COM GROUP,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"TRIP.COM GROUP,Shanghai,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111967338","display_name":"Hui Zhou","orcid":"https://orcid.org/0000-0002-7466-5350"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui Zhou","raw_affiliation_strings":["TRIP.COM GROUP,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"TRIP.COM GROUP,Shanghai,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083993732","display_name":"Chao Yang","orcid":"https://orcid.org/0000-0002-9658-050X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Yang","raw_affiliation_strings":["TRIP.COM GROUP,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"TRIP.COM GROUP,Shanghai,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056495776","display_name":"Xinyuan Qian","orcid":"https://orcid.org/0000-0002-9511-6713"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyuan Qian","raw_affiliation_strings":["University of Science and Technology Beijing,School of Computer and Communication Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing,School of Computer and Communication Engineering,Beijing,China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074514262","display_name":"Xu-Cheng Yin","orcid":"https://orcid.org/0000-0003-0023-0220"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu-Cheng Yin","raw_affiliation_strings":["University of Science and Technology Beijing,School of Computer and Communication Engineering,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing,School of Computer and Communication Engineering,Beijing,China","institution_ids":["https://openalex.org/I92403157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100685146"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.561,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78553527,"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":0.9750999808311462,"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":0.9750999808311462,"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":0.970300018787384,"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/spike","display_name":"Spike (software development)","score":0.9219140410423279},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7074441313743591},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6816883087158203},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6680663228034973},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.5266454219818115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41833949089050293},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36035871505737305},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1298709213733673}],"concepts":[{"id":"https://openalex.org/C2781390188","wikidata":"https://www.wikidata.org/wiki/Q25203449","display_name":"Spike (software development)","level":2,"score":0.9219140410423279},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7074441313743591},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6816883087158203},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6680663228034973},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.5266454219818115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41833949089050293},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36035871505737305},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1298709213733673},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","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/icassp49660.2025.10887831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887831","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/F4320331102","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2003333103","https://openalex.org/W2033310064","https://openalex.org/W2087382212","https://openalex.org/W2127141656","https://openalex.org/W2144499799","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2514741789","https://openalex.org/W2526425061","https://openalex.org/W2548332580","https://openalex.org/W2577366047","https://openalex.org/W2766219058","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963211739","https://openalex.org/W2963240019","https://openalex.org/W2963242190","https://openalex.org/W3097777922","https://openalex.org/W3160729285","https://openalex.org/W3198442913","https://openalex.org/W4283067311","https://openalex.org/W4299649720","https://openalex.org/W4319862255","https://openalex.org/W4372259951","https://openalex.org/W4385822767","https://openalex.org/W4388017359","https://openalex.org/W4391021666","https://openalex.org/W4391021768","https://openalex.org/W4392903240","https://openalex.org/W4392910591","https://openalex.org/W4402111786","https://openalex.org/W6636915900","https://openalex.org/W6675365184","https://openalex.org/W6687566353","https://openalex.org/W6839026989","https://openalex.org/W6852381208","https://openalex.org/W6857062747"],"related_works":["https://openalex.org/W2174331923","https://openalex.org/W2050175337","https://openalex.org/W2390901981","https://openalex.org/W2329992713","https://openalex.org/W3050304047","https://openalex.org/W2109115373","https://openalex.org/W2317338006","https://openalex.org/W2385487847","https://openalex.org/W2062974934","https://openalex.org/W2385476654"],"abstract_inverted_index":{"Recently,":[0],"end-to-end":[1],"automatic":[2],"speech":[3],"recognition":[4,50,144,150],"has":[5],"become":[6],"the":[7,22,80,89,102,109,117,122,132,138,143],"mainstream":[8],"approach":[9,168],"in":[10,19,127,137],"both":[11,159],"industry":[12],"and":[13,33,86,161],"academia.":[14],"To":[15],"optimize":[16],"system":[17],"performance":[18],"specific":[20],"scenarios,":[21],"Weighted":[23],"Finite-State":[24],"Transducer":[25],"(WFST)":[26],"is":[27],"extensively":[28],"used":[29],"to":[30,39,94,101,131],"integrate":[31],"acoustic":[32],"language":[34,42],"models,":[35],"leveraging":[36],"its":[37],"capacity":[38],"implicitly":[40],"fuse":[41],"models":[43],"within":[44],"static":[45],"graphs,":[46],"thereby":[47],"ensuring":[48],"robust":[49],"while":[51,141],"also":[52],"facilitating":[53],"rapid":[54],"error":[55],"correction.":[56],"However,":[57],"WFST":[58,128],"necessitates":[59],"a":[60,166],"frame-by-frame":[61],"search":[62],"of":[63,83,124,134],"CTC":[64,84,139,171],"posterior":[65],"probabilities":[66],"through":[67],"autoregression,":[68],"which":[69,114],"significantly":[70,153],"hampers":[71],"inference":[72,118],"speed.":[73],"In":[74],"this":[75],"work,":[76],"we":[77,107],"thoroughly":[78],"investigate":[79],"spike":[81],"property":[82],"outputs":[85],"further":[87],"propose":[88,108],"conjecture":[90],"that":[91],"adjacent":[92],"frames":[93,125,136],"non-blank":[95],"spikes":[96],"carry":[97],"semantic":[98],"information":[99],"beneficial":[100],"model.":[103],"Building":[104],"on":[105],"this,":[106],"Spike":[110],"Window":[111],"Decoding":[112],"algorithm,":[113],"greatly":[115],"improves":[116],"speed":[119],"by":[120],"making":[121],"number":[123,133],"decoded":[126],"linearly":[129],"related":[130],"spiking":[135],"output,":[140],"guaranteeing":[142],"performance.":[145],"Our":[146],"method":[147],"achieves":[148],"SOTA":[149],"accuracy":[151],"with":[152,173],"accelerates":[154],"decoding":[155],"speed,":[156],"proven":[157],"across":[158],"AISHELL-1":[160],"large-scale":[162],"In-House":[163],"datasets,":[164],"establishing":[165],"pioneering":[167],"for":[169],"integrating":[170],"output":[172],"WFST.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}