{"id":"https://openalex.org/W3087588949","doi":"https://doi.org/10.48550/arxiv.2009.09615","title":"End-to-End Bengali Speech Recognition","display_name":"End-to-End Bengali Speech Recognition","publication_year":2020,"publication_date":"2020-09-21","ids":{"openalex":"https://openalex.org/W3087588949","doi":"https://doi.org/10.48550/arxiv.2009.09615","mag":"3087588949"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2009.09615","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.09615","pdf_url":"https://arxiv.org/pdf/2009.09615","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2009.09615","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100686470","display_name":"Sayan Mandal","orcid":"https://orcid.org/0000-0002-0861-6905","observed_orcids":["https://orcid.org/0000-0002-0861-6905"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mandal, Sayan","raw_affiliation_strings":["Staqu Technologies , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Staqu Technologies , India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000317921","display_name":"Sarthak Yadav","orcid":"https://orcid.org/0000-0002-1979-9460","observed_orcids":["https://orcid.org/0000-0002-1979-9460"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yadav, Sarthak","raw_affiliation_strings":["Staqu Technologies , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Staqu Technologies , India","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Rai, Atul","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rai, Atul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.0,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/end-to-end-speech-recognition","display_name":"end-to-end speech recognition","score":0.9350000023841858},{"id":"https://openalex.org/keywords/ctc","display_name":"CTC","score":0.6399999856948853},{"id":"https://openalex.org/keywords/cnn-rnn","display_name":"CNN-RNN","score":0.9620000123977661},{"id":"https://openalex.org/keywords/model-compression","display_name":"model compression","score":0.4399999976158142},{"id":"https://openalex.org/keywords/parameter-efficiency","display_name":"parameter efficiency","score":0.6010000109672546},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.5410000085830688},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"word error rate","score":0.5889999866485596}],"concepts":[{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.985145092010498},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8018866181373596},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6809370517730713},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6507869958877563},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6068325042724609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5904976725578308},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5478132367134094},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5347572565078735},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5343517661094666},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5285232067108154},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5202732682228088},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.507469117641449},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4789879322052002},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4765073359012604},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3735845386981964},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3218081295490265},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2790306508541107},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10818776488304138},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2009.09615","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.09615","pdf_url":"https://arxiv.org/pdf/2009.09615","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"mag:3087588949","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2009.09615.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2009.09615","doi":"https://doi.org/10.48550/arxiv.2009.09615","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2009.09615","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2009.09615","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.09615","pdf_url":"https://arxiv.org/pdf/2009.09615","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"sustainable_development_goals_aurora":[{"score":0.5299999713897705,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1922655562","https://openalex.org/W2127141656","https://openalex.org/W2134800885","https://openalex.org/W2156876426","https://openalex.org/W2183341477","https://openalex.org/W2193413348","https://openalex.org/W2194775991","https://openalex.org/W2274287116","https://openalex.org/W2302255633","https://openalex.org/W2327501763","https://openalex.org/W2808998745","https://openalex.org/W2889082438","https://openalex.org/W2889368306","https://openalex.org/W2895676041","https://openalex.org/W2963446712","https://openalex.org/W2963993763","https://openalex.org/W2964137095"],"related_works":["https://openalex.org/W2915251951","https://openalex.org/W3200868928","https://openalex.org/W2952112541","https://openalex.org/W3094591030","https://openalex.org/W2946660022","https://openalex.org/W2895358653","https://openalex.org/W2198724430","https://openalex.org/W2761272540","https://openalex.org/W3132829453","https://openalex.org/W3142385198","https://openalex.org/W2972951785","https://openalex.org/W2896034938","https://openalex.org/W3123579023","https://openalex.org/W3089122997","https://openalex.org/W3122655227","https://openalex.org/W2963963943","https://openalex.org/W3088868295","https://openalex.org/W3019546258","https://openalex.org/W3009746329","https://openalex.org/W2965276554"],"abstract_inverted_index":{"Bengali":[0,27,54,125,149],"is":[1],"a":[2,42,159],"prominent":[3,17,43],"language":[4],"of":[5,66,84,108,117,136,142,161,167,176],"the":[6,21,53,62,78,104,112,121,134,148],"Indian":[7],"subcontinent.":[8],"However,":[9],"while":[10],"many":[11],"state-of-the-art":[12],"acoustic":[13],"models":[14],"exist":[15],"for":[16,26],"languages":[18],"spoken":[19],"in":[20,77],"region,":[22],"research":[23],"and":[24,30,60,64,69,87,99,111,132,145,179],"resources":[25],"are":[28,74],"few":[29],"far":[31],"between.":[32],"In":[33],"this":[34],"work,":[35],"we":[36,130],"apply":[37],"CTC":[38],"based":[39,46],"CNN-RNN":[40],"networks,":[41],"deep":[44,138],"learning":[45],"end-to-end":[47],"automatic":[48],"speech":[49],"recognition":[50],"technique,":[51],"to":[52],"ASR":[55,126,150],"task.":[56,151],"We":[57,91],"also":[58],"propose":[59,92],"evaluate":[61,133],"applicability":[63],"efficacy":[65],"small":[67],"7x3":[68,109],"3x3":[70,118],"convolution":[71,174],"kernels":[72,175],"which":[73],"prominently":[75],"used":[76],"computer":[79],"vision":[80],"domain":[81],"primarily":[82],"because":[83],"their":[85],"FLOPs":[86],"parameter":[88],"efficient":[89],"nature.":[90],"two":[93],"CNN":[94],"blocks,":[95],"2-layer":[96],"Block":[97,101,156],"A":[98],"4-layer":[100],"B,":[102,157],"with":[103,155,172],"first":[105],"layer":[106],"comprising":[107,115],"kernel":[110],"subsequent":[113],"layers":[114],"solely":[116],"kernels.":[119],"Using":[120],"publicly":[122],"available":[123],"Large":[124],"Training":[127],"data":[128],"set,":[129],"benchmark":[131],"performance":[135],"seven":[137],"neural":[139],"network":[140],"configurations":[141],"varying":[143],"complexities":[144],"depth":[146],"on":[147],"Our":[152],"best":[153],"model,":[154],"has":[158],"WER":[160],"13.67,":[162],"having":[163],"an":[164],"absolute":[165],"reduction":[166],"1.39%":[168],"over":[169],"comparable":[170],"model":[171],"larger":[173],"size":[177],"41x11":[178],"21x11.":[180]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}