{"id":"https://openalex.org/W3090329631","doi":"https://doi.org/10.1145/3411109.3411123","title":"A study on spoken language identification using deep neural networks","display_name":"A study on spoken language identification using deep neural networks","publication_year":2020,"publication_date":"2020-09-15","ids":{"openalex":"https://openalex.org/W3090329631","doi":"https://doi.org/10.1145/3411109.3411123","mag":"3090329631"},"language":"en","primary_location":{"id":"doi:10.1145/3411109.3411123","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3411109.3411123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Audio Mostly Conference","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/A5003364124","display_name":"Alexandra Draghici","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexandra Draghici","raw_affiliation_strings":["Fraunhofer IDMT, Ilmenau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IDMT, Ilmenau, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047532715","display_name":"Jakob Abe\u00dfer","orcid":"https://orcid.org/0000-0003-4689-7944"},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jakob Abe\u00dfer","raw_affiliation_strings":["Fraunhofer IDMT, Ilmenau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IDMT, Ilmenau, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067411318","display_name":"Hanna Lukashevich","orcid":"https://orcid.org/0000-0002-9041-9475"},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hanna Lukashevich","raw_affiliation_strings":["Fraunhofer IDMT, Ilmenau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IDMT, Ilmenau, Germany","institution_ids":["https://openalex.org/I4210138578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1144,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.93218892,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"253","last_page":"256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9988999962806702,"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":0.9987999796867371,"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":0.8431146144866943},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.8287002444267273},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6435209512710571},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6344152688980103},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.6156966090202332},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5918040871620178},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5739892721176147},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5199360251426697},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.5185719132423401},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.509432852268219},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.508927583694458},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5000693798065186},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.4734732210636139},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.436831533908844},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39380204677581787},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3264070749282837},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2606729567050934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8431146144866943},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.8287002444267273},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6435209512710571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6344152688980103},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.6156966090202332},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5918040871620178},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5739892721176147},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5199360251426697},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.5185719132423401},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.509432852268219},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.508927583694458},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5000693798065186},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4734732210636139},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.436831533908844},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39380204677581787},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3264070749282837},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2606729567050934},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3411109.3411123","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3411109.3411123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Audio Mostly Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:fraunhofer.de:N-606139","is_oa":false,"landing_page_url":"http://publica.fraunhofer.de/documents/N-606139.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer IDMT","raw_type":"Conference Paper"},{"id":"pmh:oai:publica.fraunhofer.de:publica/409130","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/409130","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2793012778","https://openalex.org/W2902518448","https://openalex.org/W2944200841","https://openalex.org/W2963604492","https://openalex.org/W3017073710","https://openalex.org/W3143835353"],"related_works":["https://openalex.org/W3153972594","https://openalex.org/W178568469","https://openalex.org/W4386302218","https://openalex.org/W4205371571","https://openalex.org/W1978764665","https://openalex.org/W2161723943","https://openalex.org/W4287124220","https://openalex.org/W2746471555","https://openalex.org/W3168177482","https://openalex.org/W1957249293"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"investigate":[4],"a":[5,48,58],"previously":[6],"proposed":[7],"algorithm":[8,26],"for":[9],"spoken":[10],"language":[11],"identification":[12],"based":[13],"on":[14],"convolutional":[15,19,59,65],"neural":[16,21,60,67],"networks":[17,68],"and":[18,37],"recurrent":[20,66],"networks.":[22],"We":[23,41],"improve":[24],"the":[25,29],"by":[27],"modifying":[28],"training":[30],"strategy":[31],"to":[32,71],"ensure":[33],"equal":[34],"class":[35],"distribution":[36],"efficient":[38],"memory":[39],"usage.":[40],"successfully":[42],"replicate":[43],"previous":[44],"experimental":[45],"findings":[46,54],"using":[47],"modified":[49],"set":[50],"of":[51,79],"languages.":[52],"Our":[53],"confirm":[55],"that":[56],"both":[57],"network":[61],"as":[62,64],"well":[63],"are":[69],"capable":[70],"learn":[72],"language-specific":[73],"patterns":[74],"in":[75],"mel":[76],"spectrogram":[77],"representations":[78],"speech":[80],"recordings.":[81]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":8}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}