{"id":"https://openalex.org/W3016167541","doi":"https://doi.org/10.1109/icassp40776.2020.9054250","title":"CIF: Continuous Integrate-And-Fire for End-To-End Speech Recognition","display_name":"CIF: Continuous Integrate-And-Fire for End-To-End Speech Recognition","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016167541","doi":"https://doi.org/10.1109/icassp40776.2020.9054250","mag":"3016167541"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5000236213","display_name":"Linhao Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Linhao Dong","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108642431","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0002-1111-1529"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000236213"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"],"apc_list":null,"apc_paid":null,"fwci":10.0162,"has_fulltext":false,"cited_by_count":103,"citation_normalized_percentile":{"value":0.98499606,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6079","last_page":"6083"},"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":0.9987999796867371,"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":0.9987000226974487,"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":0.8552356958389282},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6741675734519958},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6739712953567505},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6619228720664978},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6302287578582764},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5727638602256775},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5293462872505188},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.46245789527893066},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4490882456302643},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.44690439105033875},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.44294261932373047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3691955804824829},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11175805330276489}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8552356958389282},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6741675734519958},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6739712953567505},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6619228720664978},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6302287578582764},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5727638602256775},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5293462872505188},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.46245789527893066},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4490882456302643},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.44690439105033875},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.44294261932373047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3691955804824829},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11175805330276489},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/icassp40776.2020.9054250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W101771737","https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1526236009","https://openalex.org/W2006370340","https://openalex.org/W2076964542","https://openalex.org/W2271840356","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2514741789","https://openalex.org/W2526425061","https://openalex.org/W2577366047","https://openalex.org/W2745439869","https://openalex.org/W2750499125","https://openalex.org/W2767601419","https://openalex.org/W2889048668","https://openalex.org/W2911291251","https://openalex.org/W2913718171","https://openalex.org/W2936123380","https://openalex.org/W2936774411","https://openalex.org/W2941814890","https://openalex.org/W2944255943","https://openalex.org/W2949975180","https://openalex.org/W2953190524","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2963236196","https://openalex.org/W2963312585","https://openalex.org/W2963727906","https://openalex.org/W2963850025","https://openalex.org/W2964272710","https://openalex.org/W2972439411","https://openalex.org/W2972995428","https://openalex.org/W2973215447","https://openalex.org/W3103005696","https://openalex.org/W3217350819","https://openalex.org/W4294619417","https://openalex.org/W6621543089","https://openalex.org/W6623517193","https://openalex.org/W6694517276","https://openalex.org/W6713762819","https://openalex.org/W6745543685","https://openalex.org/W6747158283","https://openalex.org/W6754473786","https://openalex.org/W6761563299","https://openalex.org/W6780226713","https://openalex.org/W6947929050"],"related_works":["https://openalex.org/W2374317326","https://openalex.org/W2990005675","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2221419418","https://openalex.org/W2163874654"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,53,101],"novel":[6],"soft":[7],"and":[8,27,61,113],"monotonic":[9],"alignment":[10],"mechanism":[11],"used":[12],"for":[13,67],"sequence":[14],"transduction.":[15],"It":[16],"is":[17],"inspired":[18],"by":[19],"the":[20,30,46,79,86,92,109],"integrate-and-fire":[21],"model":[22,94],"in":[23,29],"spiking":[24],"neural":[25],"networks":[26],"employed":[28],"encoder-decoder":[31],"framework":[32],"consists":[33],"of":[34,82,89,106,111],"continuous":[35],"functions,":[36],"thus":[37,65],"being":[38],"named":[39],"as:":[40],"Continuous":[41],"Integrate-and-Fire":[42],"(CIF).":[43],"Applied":[44],"to":[45,77],"ASR":[47,69,121],"task,":[48],"CIF":[49],"not":[50],"only":[51],"shows":[52,95],"concise":[54],"calculation,":[55],"but":[56],"also":[57,75],"supports":[58],"online":[59],"recognition":[60],"acoustic":[62],"boundary":[63],"positioning,":[64],"suitable":[66],"various":[68],"scenarios.":[70],"Several":[71],"support":[72],"strategies":[73],"are":[74],"proposed":[76],"alleviate":[78],"unique":[80],"problems":[81],"CIF-based":[83,93],"model.":[84],"With":[85],"joint":[87],"action":[88],"these":[90],"methods,":[91],"competitive":[96],"performance.":[97],"Notably,":[98],"it":[99],"achieves":[100],"word":[102],"error":[103],"rate":[104],"(WER)":[105],"2.86%":[107],"on":[108,118],"test-clean":[110],"Librispeech":[112],"creates":[114],"new":[115],"state-of-the-art":[116],"result":[117],"Mandarin":[119],"telephone":[120],"benchmark.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":11}],"updated_date":"2026-03-14T06:41:57.775601","created_date":"2025-10-10T00:00:00"}