{"id":"https://openalex.org/W3198614518","doi":"https://doi.org/10.21437/interspeech.2021-2084","title":"Raw Waveform Encoder with Multi-Scale Globally Attentive Locally Recurrent Networks for End-to-End Speech Recognition","display_name":"Raw Waveform Encoder with Multi-Scale Globally Attentive Locally Recurrent Networks for End-to-End Speech Recognition","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198614518","doi":"https://doi.org/10.21437/interspeech.2021-2084","mag":"3198614518"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-2084","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2084","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5102313170","display_name":"Max W. Y. Lam","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Max W.Y. Lam","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110195480","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0001-8932-6661"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106404246","display_name":"Chao Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Weng","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1399,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56183464,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"316","last_page":"320"},"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.7934409379959106},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.78934645652771},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6451456546783447},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6201488375663757},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5502762794494629},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5003616809844971},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.49967479705810547},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4779472351074219},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4451545178890228},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4200791120529175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7934409379959106},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.78934645652771},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6451456546783447},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6201488375663757},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5502762794494629},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5003616809844971},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.49967479705810547},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4779472351074219},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4451545178890228},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4200791120529175},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-2084","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2084","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1828163288","https://openalex.org/W1924770834","https://openalex.org/W1969851134","https://openalex.org/W2087992518","https://openalex.org/W2116261113","https://openalex.org/W2148154194","https://openalex.org/W2327501763","https://openalex.org/W2545177271","https://openalex.org/W2889048668","https://openalex.org/W2889163603","https://openalex.org/W2890536590","https://openalex.org/W2891874693","https://openalex.org/W2903799412","https://openalex.org/W2952218014","https://openalex.org/W2962901777","https://openalex.org/W2963071736","https://openalex.org/W2963414781","https://openalex.org/W2963669405","https://openalex.org/W2973053574","https://openalex.org/W3007227084","https://openalex.org/W3011207290","https://openalex.org/W3015199127","https://openalex.org/W3094855746","https://openalex.org/W3095697114","https://openalex.org/W3097777922","https://openalex.org/W3146854175","https://openalex.org/W3160903688","https://openalex.org/W3161532853","https://openalex.org/W3163793923","https://openalex.org/W3175785186","https://openalex.org/W4320930577","https://openalex.org/W4385245566","https://openalex.org/W4394666973"],"related_works":["https://openalex.org/W1974895211","https://openalex.org/W2129841057","https://openalex.org/W2176409448","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2144773493"],"abstract_inverted_index":{"End-to-end":[0],"speech":[1,82,149],"recognition":[2],"generally":[3],"uses":[4],"hand-engineered":[5],"acoustic":[6,69],"features":[7,24,133],"as":[8,47],"input":[9],"and":[10,22,25,42,53,78,88,94,121,134],"excludes":[11],"the":[12,130,136],"feature":[13],"extraction":[14],"module":[15],"from":[16,111],"its":[17],"joint":[18],"optimization.To":[19],"extract":[20],"learnable":[21],"adaptive":[23],"mitigate":[26],"information":[27,66],"loss,":[28],"we":[29],"propose":[30],"a":[31,74,142,146],"new":[32],"encoder":[33,103],"that":[34],"adopts":[35],"globally":[36],"attentive":[37],"locally":[38],"recurrent":[39],"(GALR)":[40],"networks":[41],"directly":[43],"takes":[44],"raw":[45],"waveform":[46,102],"input.We":[48],"observe":[49],"improved":[50],"ASR":[51],"performance":[52],"robustness":[54,128],"by":[55,141],"applying":[56],"GALR":[57,101],"on":[58,73,145],"different":[59],"window":[60],"lengths":[61],"to":[62,113],"aggregate":[63],"fine-grain":[64],"temporal":[65],"into":[67],"multi-scale":[68,100],"features.Experiments":[70],"are":[71],"conducted":[72],"benchmark":[75],"dataset":[76],"AISHELL-2":[77],"two":[79],"large-scale":[80],"Mandarin":[81],"corpus":[83],"of":[84],"5,":[85],"000":[86,90],"hours":[87],"21,":[89],"hours.With":[91],"faster":[92],"speed":[93],"comparable":[95],"model":[96,140],"size,":[97],"our":[98,124],"proposed":[99],"achieved":[104],"consistent":[105],"character":[106],"error":[107],"rate":[108],"reductions":[109],"(CERRs)":[110],"7.9%":[112],"28.1%":[114],"relative":[115],"over":[116],"strong":[117],"baselines,":[118],"including":[119],"Conformer":[120],"TDNN-Conformer.In":[122],"particular,":[123],"approach":[125],"demonstrated":[126],"notable":[127],"than":[129],"traditional":[131],"handcrafted":[132],"outperformed":[135],"baseline":[137],"MFCC-based":[138],"TDNN-Conformer":[139],"15.2%":[143],"CERR":[144],"music-mixed":[147],"real-world":[148],"test":[150],"set.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}