{"id":"https://openalex.org/W4372269205","doi":"https://doi.org/10.1109/icassp49357.2023.10094820","title":"Improving CTC-Based ASR Models With Gated Interlayer Collaboration","display_name":"Improving CTC-Based ASR Models With Gated Interlayer Collaboration","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372269205","doi":"https://doi.org/10.1109/icassp49357.2023.10094820"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094820","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/A5028185223","display_name":"Yuting Yang","orcid":"https://orcid.org/0000-0003-4260-4550"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuting Yang","raw_affiliation_strings":["NetEase Yidun AI Lab,Hangzhou,China","NetEase Yidun AI Lab, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Yidun AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"NetEase Yidun AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100697204","display_name":"Yuke Li","orcid":"https://orcid.org/0009-0000-7282-8964"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuke Li","raw_affiliation_strings":["NetEase Yidun AI Lab,Hangzhou,China","NetEase Yidun AI Lab, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Yidun AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"NetEase Yidun AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001063248","display_name":"Binbin Du","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binbin Du","raw_affiliation_strings":["NetEase Yidun AI Lab,Hangzhou,China","NetEase Yidun AI Lab, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Yidun AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"NetEase Yidun AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210091137"],"apc_list":null,"apc_paid":null,"fwci":1.7743,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.87572075,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T10028","display_name":"Topic Modeling","score":0.9947999715805054,"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/softmax-function","display_name":"Softmax function","score":0.9557653069496155},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.776357114315033},{"id":"https://openalex.org/keywords/conditional-independence","display_name":"Conditional independence","score":0.6467620134353638},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6091257333755493},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5944942235946655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5412002205848694},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5365718603134155},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5342038869857788},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.5209113955497742},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.51717609167099},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47172561287879944},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37817198038101196},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.14962583780288696},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08493077754974365}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.9557653069496155},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.776357114315033},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.6467620134353638},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6091257333755493},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5944942235946655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5412002205848694},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5365718603134155},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5342038869857788},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.5209113955497742},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.51717609167099},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47172561287879944},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37817198038101196},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14962583780288696},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08493077754974365},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094820","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1828163288","https://openalex.org/W1922655562","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2251321385","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2603679025","https://openalex.org/W2739427748","https://openalex.org/W2884254529","https://openalex.org/W2884975363","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2962826786","https://openalex.org/W2963211739","https://openalex.org/W2963242190","https://openalex.org/W2963414781","https://openalex.org/W2963827914","https://openalex.org/W3015537910","https://openalex.org/W3016010032","https://openalex.org/W3097777922","https://openalex.org/W3141854550","https://openalex.org/W3162249256","https://openalex.org/W3162899666","https://openalex.org/W3163793923","https://openalex.org/W3197140813","https://openalex.org/W3205920203","https://openalex.org/W3206573929","https://openalex.org/W4200629210","https://openalex.org/W4385245566","https://openalex.org/W6675365184","https://openalex.org/W6691770337","https://openalex.org/W6739901393","https://openalex.org/W6753411874","https://openalex.org/W6773475747"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W3108503355","https://openalex.org/W3090555870","https://openalex.org/W4226420367","https://openalex.org/W2962876041","https://openalex.org/W3022820045","https://openalex.org/W1773599773","https://openalex.org/W2042697870","https://openalex.org/W2268150819"],"abstract_inverted_index":{"The":[0,89],"CTC-based":[1,39,56],"automatic":[2],"speech":[3],"recognition":[4],"(ASR)":[5],"models":[6],"without":[7],"the":[8,14,36,46,51,61,68,75,79,115],"external":[9],"language":[10],"model":[11,17,47],"usually":[12],"lack":[13],"capacity":[15],"to":[16,34],"conditional":[18,52],"dependencies":[19],"and":[20,48,109],"textual":[21,43,69,90],"interactions.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26,59],"present":[27],"a":[28,100],"Gated":[29],"Interlayer":[30],"Collaboration":[31],"(GIC)":[32],"mechanism":[33],"improve":[35],"performance":[37],"of":[38,55,64],"models,":[40],"which":[41],"introduces":[42],"information":[44],"into":[45],"thus":[49],"relaxes":[50],"independence":[53],"assumption":[54],"models.":[57],"Specifically,":[58],"consider":[60],"weighted":[62],"sum":[63],"token":[65],"embeddings":[66],"as":[67],"representation":[70],"for":[71],"each":[72],"position,":[73],"where":[74],"position-specific":[76],"weights":[77],"are":[78,92],"softmax":[80],"probability":[81],"distribution":[82],"constructed":[83],"via":[84],"inter-layer":[85],"auxiliary":[86],"CTC":[87],"losses.":[88],"representations":[91],"then":[93],"fused":[94],"with":[95],"acoustic":[96],"features":[97],"by":[98],"developing":[99],"gate":[101],"unit.":[102],"Experiments":[103],"on":[104],"AISHELL-1":[105],"[1],":[106],"TEDLIUM2":[107],"[2],":[108],"AI-DATATANG":[110],"[3]":[111],"corpora":[112],"show":[113],"that":[114],"proposed":[116],"method":[117],"outperforms":[118],"several":[119],"strong":[120],"baselines.":[121]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}