{"id":"https://openalex.org/W4367694395","doi":"https://doi.org/10.48550/arxiv.2305.00417","title":"Transformer-based Sequence Labeling for Audio Classification based on MFCCs","display_name":"Transformer-based Sequence Labeling for Audio Classification based on MFCCs","publication_year":2023,"publication_date":"2023-04-30","ids":{"openalex":"https://openalex.org/W4367694395","doi":"https://doi.org/10.48550/arxiv.2305.00417"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2305.00417","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.00417","pdf_url":"https://arxiv.org/pdf/2305.00417","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/2305.00417","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063945188","display_name":"C. S. Sonali","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sonali, C. S.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069869400","display_name":"B S Chinmayi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S, Chinmayi B","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005963613","display_name":"Ahana Balasubramanian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Balasubramanian, Ahana","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":false,"cited_by_count":0,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.00019999999494757503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/audio-classification","display_name":"audio classification","score":0.9990000128746033},{"id":"https://openalex.org/keywords/mel-frequency-cepstral-coefficients","display_name":"Mel-frequency cepstral coefficients","score":0.8840000033378601},{"id":"https://openalex.org/keywords/transformer-encoder","display_name":"Transformer encoder","score":0.777999997138977},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"sequence labeling","score":0.9580000042915344},{"id":"https://openalex.org/keywords/spectrogram-classification","display_name":"spectrogram classification","score":0.7459999918937683},{"id":"https://openalex.org/keywords/lightweight-models","display_name":"lightweight models","score":0.6899999976158142},{"id":"https://openalex.org/keywords/esc-50","display_name":"ESC-50","score":0.9049999713897705},{"id":"https://openalex.org/keywords/voice-commands","display_name":"voice commands","score":0.8579999804496765},{"id":"https://openalex.org/keywords/urbansound8k","display_name":"UrbanSound8K","score":0.9440000057220459},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.4519999921321869},{"id":"https://openalex.org/keywords/music-recognition","display_name":"music recognition","score":0.9049999713897705}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.897365927696228},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7811850309371948},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6051502227783203},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6015720367431641},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5576773285865784},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5420637130737305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5348642468452454},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5055098533630371},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.481766939163208},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.47163650393486023},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4577310383319855},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41523411870002747},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3507753312587738},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3179449439048767},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09211435914039612},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2305.00417","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.00417","pdf_url":"https://arxiv.org/pdf/2305.00417","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":"doi:10.48550/arxiv.2305.00417","doi":"https://doi.org/10.48550/arxiv.2305.00417","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.00417","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.00417","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.00417","pdf_url":"https://arxiv.org/pdf/2305.00417","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":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.8700000047683716}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W3013693939","https://openalex.org/W2088854863","https://openalex.org/W2159052453","https://openalex.org/W4360764600","https://openalex.org/W2555630001","https://openalex.org/W2109142991","https://openalex.org/W2350061705"],"abstract_inverted_index":{"Audio":[0],"classification":[1,70,84,138],"is":[2,23],"vital":[3],"in":[4,27,71],"areas":[5],"such":[6,18],"as":[7,19],"speech":[8],"and":[9,21,46,97,100],"music":[10],"recognition.":[11],"Feature":[12],"extraction":[13],"from":[14],"the":[15,92,106,114,117,136],"audio":[16,28,83,137],"signal,":[17],"Mel-Spectrograms":[20],"MFCCs,":[22],"a":[24,63,79,124],"critical":[25],"step":[26],"classification.":[29,37],"These":[30],"features":[31],"are":[32],"transformed":[33],"into":[34],"spectrograms":[35],"for":[36,82],"Researchers":[38],"have":[39],"explored":[40],"various":[41],"techniques,":[42],"including":[43],"traditional":[44],"machine":[45],"deep":[47],"learning":[48],"methods":[49],"to":[50],"classify":[51],"spectrograms,":[52],"but":[53],"these":[54],"can":[55,73],"be":[56,74],"computationally":[57],"expensive.":[58],"To":[59],"simplify":[60],"this":[61],"process,":[62],"more":[64],"straightforward":[65],"approach":[66],"inspired":[67],"by":[68],"sequence":[69],"NLP":[72],"used.":[75],"This":[76],"paper":[77],"proposes":[78],"Transformer-encoder-based":[80],"model":[81,88,115,121],"using":[85],"MFCCs.":[86],"The":[87,120],"was":[89],"benchmarked":[90],"against":[91],"ESC-50,":[93],"Speech":[94],"Commands":[95],"v0.02":[96],"UrbanSound8k":[98,118],"datasets":[99],"has":[101],"shown":[102],"strong":[103],"performance,":[104],"with":[105],"highest":[107],"accuracy":[108],"of":[109,123],"95.2%":[110],"obtained":[111],"upon":[112],"training":[113],"on":[116],"dataset.":[119],"consisted":[122],"mere":[125],"127,544":[126],"total":[127],"parameters,":[128],"making":[129],"it":[130],"light-weight":[131],"yet":[132],"highly":[133],"efficient":[134],"at":[135],"task.":[139]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}