{"id":"https://openalex.org/W3007537117","doi":"https://doi.org/10.1109/asru46091.2019.9003784","title":"An Investigation of LSTM-CTC based Joint Acoustic Model for Indian Language Identification","display_name":"An Investigation of LSTM-CTC based Joint Acoustic Model for Indian Language Identification","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007537117","doi":"https://doi.org/10.1109/asru46091.2019.9003784","mag":"3007537117"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003784","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003784","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5074027866","display_name":"Tirusha Mandava","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Tirusha Mandava","raw_affiliation_strings":["Speech Processing Laboratory, International Institute of Information Technology, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Speech Processing Laboratory, International Institute of Information Technology, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081796698","display_name":"Ravi Kumar Vuddagiri","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ravi Kumar Vuddagiri","raw_affiliation_strings":["Speech Processing Laboratory, International Institute of Information Technology, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Speech Processing Laboratory, International Institute of Information Technology, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014351336","display_name":"Hari Krishna Vydana","orcid":"https://orcid.org/0000-0001-5192-5888"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hari Krishna Vydana","raw_affiliation_strings":["Speech Processing Laboratory, International Institute of Information Technology, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Speech Processing Laboratory, International Institute of Information Technology, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007569113","display_name":"Anil Kumar Vuppala","orcid":"https://orcid.org/0000-0001-7795-0408"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anil Kumar Vuppala","raw_affiliation_strings":["Speech Processing Laboratory, International Institute of Information Technology, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Speech Processing Laboratory, International Institute of Information Technology, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5074027866"],"corresponding_institution_ids":["https://openalex.org/I64189192"],"apc_list":null,"apc_paid":null,"fwci":0.28,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67868233,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"389","last_page":"396"},"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":0.9980000257492065,"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":0.9952999949455261,"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":0.8239099979400635},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6328449249267578},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6309835910797119},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.618661642074585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6047650575637817},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6003624796867371},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5789476037025452},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5780655741691589},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5013415813446045},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.44583559036254883},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.43542179465293884},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43223094940185547},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41115429997444153},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08664354681968689}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8239099979400635},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6328449249267578},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6309835910797119},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.618661642074585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6047650575637817},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6003624796867371},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5789476037025452},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5780655741691589},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5013415813446045},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.44583559036254883},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.43542179465293884},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43223094940185547},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41115429997444153},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08664354681968689},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"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/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003784","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003784","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W47263812","https://openalex.org/W1490504384","https://openalex.org/W1491198847","https://openalex.org/W1969121061","https://openalex.org/W1972300018","https://openalex.org/W1986689944","https://openalex.org/W2026411533","https://openalex.org/W2045801524","https://openalex.org/W2091409162","https://openalex.org/W2095501777","https://openalex.org/W2127581356","https://openalex.org/W2153181479","https://openalex.org/W2175575774","https://openalex.org/W2185814970","https://openalex.org/W2296178052","https://openalex.org/W2397236868","https://openalex.org/W2404292690","https://openalex.org/W2406215990","https://openalex.org/W2406392101","https://openalex.org/W2408021097","https://openalex.org/W2500968368","https://openalex.org/W2510374792","https://openalex.org/W2772654302","https://openalex.org/W2794506738","https://openalex.org/W2889206025","https://openalex.org/W2889519245","https://openalex.org/W2895103375","https://openalex.org/W2895547158","https://openalex.org/W2963063081","https://openalex.org/W2963307329","https://openalex.org/W2964309797","https://openalex.org/W2972645685","https://openalex.org/W3148232083","https://openalex.org/W6601939451","https://openalex.org/W6661873022","https://openalex.org/W6697259356","https://openalex.org/W6712620166","https://openalex.org/W6713629195","https://openalex.org/W6714096116"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","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","https://openalex.org/W1494724239"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"phonetic":[3,106],"features":[4,30,48,68,80,102],"derived":[5],"from":[6],"the":[7,36,66,130,138],"joint":[8],"acoustic":[9],"model":[10,131],"(JAM)":[11],"of":[12,89,120],"a":[13,74],"multilingual":[14],"end":[15,17],"to":[16,51],"automatic":[18],"speech":[19],"recognition":[20],"system":[21],"are":[22,49],"proposed":[23,79],"for":[24],"Indian":[25,92,95],"language":[26],"identification":[27],"(LID).":[28],"These":[29],"utilize":[31],"contextual":[32],"information":[33],"learned":[34],"by":[35,69],"JAM":[37],"through":[38,73],"long":[39],"short-term":[40],"memory-connectionist":[41],"temporal":[42,107],"classification":[43],"(LSTM-CTC)":[44],"framework.":[45],"Hence,":[46],"these":[47,62],"referred":[50],"as":[52],"CTC":[53,101,125],"features.":[54],"A":[55],"multi-head":[56],"self-attention":[57],"network":[58],"is":[59],"trained":[60],"using":[61],"features,":[63],"which":[64],"aggregates":[65],"frame-level":[67],"selecting":[70],"prominent":[71],"frames":[72],"parametrized":[75],"attention":[76],"layer.":[77],"The":[78,118],"have":[81],"been":[82],"tested":[83],"on":[84],"IIITH-ILSC":[85],"database":[86],"that":[87,100],"consists":[88],"22":[90],"official":[91],"languages":[93],"and":[94,105,111,124,133],"English.":[96],"Experimental":[97],"results":[98],"demonstrate":[99],"outperformed":[103],"i-vector":[104],"neural":[108],"LID":[109,127],"systems":[110,128],"produced":[112],"an":[113],"8.70%":[114],"equal":[115],"error":[116],"rate.":[117],"fusion":[119],"shifted":[121],"delta":[122],"cepstral":[123],"feature-based":[126],"at":[129],"level":[132,135],"feature":[134],"further":[136],"improved":[137],"performance.":[139]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}