{"id":"https://openalex.org/W4283692355","doi":"https://doi.org/10.1109/spcom55316.2022.9840823","title":"On Comparison of Encoders for Attention based End to End Speech Recognition in Standalone and Rescoring Mode","display_name":"On Comparison of Encoders for Attention based End to End Speech Recognition in Standalone and Rescoring Mode","publication_year":2022,"publication_date":"2022-07-11","ids":{"openalex":"https://openalex.org/W4283692355","doi":"https://doi.org/10.1109/spcom55316.2022.9840823"},"language":"en","primary_location":{"id":"doi:10.1109/spcom55316.2022.9840823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom55316.2022.9840823","pdf_url":null,"source":{"id":"https://openalex.org/S4363608579","display_name":"2022 IEEE International Conference on Signal Processing and Communications (SPCOM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Signal Processing and Communications (SPCOM)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2206.12829","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009725385","display_name":"Raviraj Joshi","orcid":"https://orcid.org/0000-0003-1892-1812"},"institutions":[{"id":"https://openalex.org/I4210090636","display_name":"Wipro (India)","ror":"https://ror.org/001ccf545","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210090636"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Raviraj Joshi","raw_affiliation_strings":["Flipkart Internet Pvt. Ltd.,Bengaluru,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Flipkart Internet Pvt. Ltd.,Bengaluru,India","institution_ids":["https://openalex.org/I4210090636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055055138","display_name":"Subodh Kumar","orcid":"https://orcid.org/0000-0003-0874-8163"},"institutions":[{"id":"https://openalex.org/I4210090636","display_name":"Wipro (India)","ror":"https://ror.org/001ccf545","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210090636"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Subodh Kumar","raw_affiliation_strings":["Flipkart Internet Pvt. Ltd.,Bengaluru,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Flipkart Internet Pvt. Ltd.,Bengaluru,India","institution_ids":["https://openalex.org/I4210090636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210090636"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8810999989509583,"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":0.8810999989509583,"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":0.06530000269412994,"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":0.00989999994635582,"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":0.8204448223114014},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6557040214538574},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6437457799911499},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6435146331787109},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6418883204460144},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4976990520954132},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.47651493549346924},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4454600512981415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34036076068878174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8204448223114014},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6557040214538574},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6437457799911499},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6435146331787109},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6418883204460144},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4976990520954132},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.47651493549346924},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4454600512981415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34036076068878174},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/spcom55316.2022.9840823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom55316.2022.9840823","pdf_url":null,"source":{"id":"https://openalex.org/S4363608579","display_name":"2022 IEEE International Conference on Signal Processing and Communications (SPCOM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Signal Processing and Communications (SPCOM)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2206.12829","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.12829","pdf_url":"https://arxiv.org/pdf/2206.12829","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2206.12829","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2206.12829","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2206.12829","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.12829","pdf_url":"https://arxiv.org/pdf/2206.12829","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2143612262","https://openalex.org/W2327501763","https://openalex.org/W2627092829","https://openalex.org/W2936774411","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2963240019","https://openalex.org/W2963250244","https://openalex.org/W2963414781","https://openalex.org/W2963979492","https://openalex.org/W3011339933","https://openalex.org/W3015194534","https://openalex.org/W3015752032","https://openalex.org/W3015927303","https://openalex.org/W3093312917","https://openalex.org/W3095994005","https://openalex.org/W3097777922","https://openalex.org/W3141464856","https://openalex.org/W3217314497","https://openalex.org/W4221160683","https://openalex.org/W4283689058","https://openalex.org/W6638749077","https://openalex.org/W6639156005","https://openalex.org/W6679434410","https://openalex.org/W6770528390"],"related_works":["https://openalex.org/W12168553","https://openalex.org/W14230040","https://openalex.org/W7946549","https://openalex.org/W2308727","https://openalex.org/W6143937","https://openalex.org/W7401400","https://openalex.org/W1745277","https://openalex.org/W11060696","https://openalex.org/W1679128","https://openalex.org/W1226999"],"abstract_inverted_index":{"The":[0,52],"streaming":[1,38],"automatic":[2],"speech":[3],"recognition":[4],"(ASR)":[5],"models":[6,17,58,74,88,115],"are":[7,89],"more":[8],"popular":[9],"and":[10,84,106],"suitable":[11],"for":[12],"voice-based":[13],"applications.":[14],"However,":[15],"non-streaming":[16,35,63,70],"provide":[18,186],"better":[19],"performance":[20,193],"as":[21],"they":[22],"look":[23],"at":[24],"the":[25,31,34,69,76,110,124,131,145,158,178,184,190],"entire":[26],"audio":[27],"context.":[28],"To":[29],"leverage":[30],"benefits":[32,188],"of":[33,113,141,160],"model":[36,126],"in":[37,47,81,177,192,196],"applications":[39],"like":[40],"voice":[41,78],"search,":[42],"it":[43],"is":[44,59,194],"commonly":[45],"used":[46],"second":[48,146,179],"pass":[49,147,180],"re-scoring":[50,85,181],"mode.":[51,200],"candidate":[53],"hypothesis":[54],"generated":[55],"using":[56,61],"steaming":[57],"re-scored":[60],"a":[62,137],"model.In":[64],"this":[65],"work,":[66],"we":[67,121,174],"evaluate":[68],"attention-based":[71],"end-to-end":[72],"ASR":[73],"on":[75,91,103],"Flipkart":[77],"search":[79],"task":[80],"both":[82],"standalone":[83,197],"modes.":[86],"These":[87],"based":[90,102],"Listen-Attend-Spell":[92],"(LAS)":[93],"encoder-decoder":[94],"architecture.":[95],"We":[96,108,135,155],"experiment":[97],"with":[98,117,130,144,150,163],"different":[99],"encoder":[100],"variations":[101],"LSTM,":[104],"Transformer,":[105],"Conformer.":[107],"compare":[109],"latency":[111,133,151],"requirements":[112],"these":[114],"along":[116],"their":[118],"performance.":[119],"Overall":[120],"show":[122],"that":[123,176],"Transformer":[125,164],"offers":[127],"acceptable":[128],"WER":[129,139],"lowest":[132],"requirements.":[134],"report":[136],"relative":[138],"improvement":[140],"around":[142],"16%":[143],"LAS":[148],"rescoring":[149],"overhead":[152],"under":[153],"5ms.":[154],"also":[156],"highlight":[157],"importance":[159],"CNN":[161],"front-end":[162],"architecture":[165],"to":[166],"achieve":[167],"comparable":[168],"word":[169],"error":[170],"rates":[171],"(WER).":[172],"Moreover,":[173],"observe":[175],"mode":[182],"all":[183],"encoders":[185],"similar":[187],"whereas":[189],"difference":[191],"prominent":[195],"text":[198],"generation":[199]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-06-30T00:00:00"}