{"id":"https://openalex.org/W4289139345","doi":"https://doi.org/10.25080/majora-212e5952-017","title":"pyAudioProcessing: Audio Processing, Feature Extraction, and Machine Learning Modeling","display_name":"pyAudioProcessing: Audio Processing, Feature Extraction, and Machine Learning Modeling","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4289139345","doi":"https://doi.org/10.25080/majora-212e5952-017"},"language":"en","primary_location":{"id":"doi:10.25080/majora-212e5952-017","is_oa":true,"landing_page_url":"https://doi.org/10.25080/majora-212e5952-017","pdf_url":"http://conference.scipy.org/proceedings/scipy2022/pdfs/jyotika_singh.pdf","source":{"id":"https://openalex.org/S4220651651","display_name":"Proceedings of the Python in Science Conferences","issn_l":"2575-9752","issn":["2575-9752"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Python in Science Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"http://conference.scipy.org/proceedings/scipy2022/pdfs/jyotika_singh.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101916711","display_name":"Jyotika Singh","orcid":"https://orcid.org/0000-0002-5442-3004"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jyotika Singh","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5442-3004","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101916711"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1488,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39259506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"152","last_page":"158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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":0.9976999759674072,"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":0.963699996471405,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9538999795913696,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8408808708190918},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8321937918663025},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.803428053855896},{"id":"https://openalex.org/keywords/matlab","display_name":"MATLAB","score":0.5936046838760376},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5653648376464844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5412944555282593},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5216967463493347},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5089967250823975},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.44122010469436646},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.375870019197464},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.30023062229156494},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.23164546489715576},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12761491537094116}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8408808708190918},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8321937918663025},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.803428053855896},{"id":"https://openalex.org/C2780365114","wikidata":"https://www.wikidata.org/wiki/Q169478","display_name":"MATLAB","level":2,"score":0.5936046838760376},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5653648376464844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5412944555282593},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5216967463493347},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5089967250823975},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.44122010469436646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.375870019197464},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.30023062229156494},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.23164546489715576},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12761491537094116}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.25080/majora-212e5952-017","is_oa":true,"landing_page_url":"https://doi.org/10.25080/majora-212e5952-017","pdf_url":"http://conference.scipy.org/proceedings/scipy2022/pdfs/jyotika_singh.pdf","source":{"id":"https://openalex.org/S4220651651","display_name":"Proceedings of the Python in Science Conferences","issn_l":"2575-9752","issn":["2575-9752"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Python in Science Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.25080/majora-212e5952-017","is_oa":true,"landing_page_url":"https://doi.org/10.25080/majora-212e5952-017","pdf_url":"http://conference.scipy.org/proceedings/scipy2022/pdfs/jyotika_singh.pdf","source":{"id":"https://openalex.org/S4220651651","display_name":"Proceedings of the Python in Science Conferences","issn_l":"2575-9752","issn":["2575-9752"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Python in Science Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4289139345.pdf","grobid_xml":"https://content.openalex.org/works/W4289139345.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2385545","https://openalex.org/W1835965142","https://openalex.org/W2007645738","https://openalex.org/W2054446408","https://openalex.org/W2192412620","https://openalex.org/W2530400070","https://openalex.org/W2725868244","https://openalex.org/W3169721945","https://openalex.org/W3217294474","https://openalex.org/W4239452971","https://openalex.org/W4245024876","https://openalex.org/W4288076474","https://openalex.org/W6885006380","https://openalex.org/W6968748856"],"related_works":["https://openalex.org/W2980163522","https://openalex.org/W4226047925","https://openalex.org/W2289868279","https://openalex.org/W2555630001","https://openalex.org/W4315836293","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W2389015249","https://openalex.org/W2970176078","https://openalex.org/W2157165686"],"abstract_inverted_index":{"pyAudioProcessing":[0,88],"is":[1,37,205,210],"a":[2,38,44,66,195],"Python":[3,59,81],"based":[4],"library":[5,76,204],"for":[6,43,65],"processing":[7,54],"audio":[8,29,51,97,156,169,178],"data,":[9],"constructing":[10],"and":[11,18,23,52,73,114,119,174,177,192,209],"extracting":[12],"numerical":[13],"features":[14,78,95,121,128],"from":[15,96,122,154],"audio,":[16],"building":[17],"testing":[19],"machine":[20,70,186],"learning":[21,71,187],"models,":[22],"classifying":[24],"data":[25,189],"with":[26,130,167,194],"existing":[27],"pre-trained":[28],"classification":[30,133],"models":[31,199],"or":[32,135],"custom":[33],"user-built":[34],"models.":[35],"MATLAB":[36],"popular":[39,139],"language":[40,62],"of":[41,47,63,69,137,160,197],"choice":[42,64],"vast":[45,67],"amount":[46],"research":[48,72],"in":[49,80,86],"the":[50,57,61,90,138,155,161],"speech":[53],"domain.":[55],"On":[56],"contrary,":[58],"remains":[60],"majority":[68],"functionality.":[74],"This":[75,181],"contains":[77,165],"built":[79],"that":[82,142],"were":[83],"originally":[84],"published":[85],"MATLAB.":[87],"allows":[89],"user":[91],"to":[92,150,184,200],"compute":[93],"various":[94],"files":[98],"including":[99],"Gammatone":[100],"Frequency":[101,106],"Cepstral":[102,107],"Coefficients":[103,108],"(GFCC),":[104],"Mel":[105],"(MFCC),":[109],"spectral":[110],"features,":[111,113],"chroma":[112],"others":[115],"such":[116,171],"as":[117,172],"beat-based":[118],"cepstrum-based":[120],"audio.":[123,202],"One":[124],"can":[125],"use":[126],"these":[127],"along":[129],"one's":[131],"own":[132],"backend":[134],"any":[136],"scikit-learn":[140],"classifiers":[141],"have":[143],"been":[144],"integrated":[145],"into":[146],"pyAudioProcessing.":[147],"Cleaning":[148],"functions":[149],"strip":[151],"unwanted":[152],"portions":[153],"are":[157],"another":[158],"offering":[159],"library.":[162],"It":[163],"further":[164],"integrations":[166],"other":[168],"functionalities":[170],"frequency":[173],"time-series":[175],"visualizations":[176],"format":[179],"conversions.":[180],"software":[182],"aims":[183],"provide":[185],"engineers,":[188],"scientists,":[190],"researchers,":[191],"students":[193],"set":[196],"baseline":[198],"classify":[201],"The":[203],"available":[206],"at":[207],"https://github.com/jsingh811/pyAudioProcessing":[208],"under":[211]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}