{"id":"https://openalex.org/W4319586325","doi":"https://doi.org/10.1109/iscslp57327.2022.10037931","title":"Data Augmentation for Infant Cry Classification","display_name":"Data Augmentation for Infant Cry Classification","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319586325","doi":"https://doi.org/10.1109/iscslp57327.2022.10037931"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10037931","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10037931","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5071023061","display_name":"Aastha Kachhi","orcid":"https://orcid.org/0009-0002-2212-8606"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aastha Kachhi","raw_affiliation_strings":["Speech Research Lab, DA-IICT,Gandhinagar,India","Speech Research Lab, DA-IICT, Gandhinagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Lab, DA-IICT,Gandhinagar,India","institution_ids":["https://openalex.org/I98389781"]},{"raw_affiliation_string":"Speech Research Lab, DA-IICT, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103987250","display_name":"Shreya S. Chaturvedi","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shreya Chaturvedi","raw_affiliation_strings":["Speech Research Lab, DA-IICT,Gandhinagar,India","Speech Research Lab, DA-IICT, Gandhinagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Lab, DA-IICT,Gandhinagar,India","institution_ids":["https://openalex.org/I98389781"]},{"raw_affiliation_string":"Speech Research Lab, DA-IICT, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043002276","display_name":"Hemant A. Patil","orcid":"https://orcid.org/0000-0002-4068-2005"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant A. Patil","raw_affiliation_strings":["Speech Research Lab, DA-IICT,Gandhinagar,India","Speech Research Lab, DA-IICT, Gandhinagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Lab, DA-IICT,Gandhinagar,India","institution_ids":["https://openalex.org/I98389781"]},{"raw_affiliation_string":"Speech Research Lab, DA-IICT, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006494479","display_name":"Dipesh K. Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dipesh Kumar Singh","raw_affiliation_strings":["Speech Research Lab, DA-IICT,Gandhinagar,India","Speech Research Lab, DA-IICT, Gandhinagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Lab, DA-IICT,Gandhinagar,India","institution_ids":["https://openalex.org/I98389781"]},{"raw_affiliation_string":"Speech Research Lab, DA-IICT, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98389781"],"apc_list":null,"apc_paid":null,"fwci":10.5,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.98802395,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"433","last_page":"437"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13289","display_name":"Infant Health and Development","score":1.0,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T13289","display_name":"Infant Health and Development","score":1.0,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9959999918937683,"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":0.9902999997138977,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.9179513454437256},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.7346753478050232},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6584569215774536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5029422640800476},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4885317087173462},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4861690402030945},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.46834155917167664},{"id":"https://openalex.org/keywords/perturbation","display_name":"Perturbation (astronomy)","score":0.4262534976005554},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3032550811767578},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11519157886505127}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.9179513454437256},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.7346753478050232},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6584569215774536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5029422640800476},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4885317087173462},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4861690402030945},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46834155917167664},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.4262534976005554},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3032550811767578},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11519157886505127},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10037931","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10037931","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/1","display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W20528612","https://openalex.org/W1586405805","https://openalex.org/W2023725399","https://openalex.org/W2066269541","https://openalex.org/W2136472617","https://openalex.org/W2147348451","https://openalex.org/W2148154194","https://openalex.org/W2152575748","https://openalex.org/W2168510624","https://openalex.org/W2259135914","https://openalex.org/W2399892072","https://openalex.org/W2407080277","https://openalex.org/W2522286455","https://openalex.org/W2769035248","https://openalex.org/W2972459675","https://openalex.org/W3126759488","https://openalex.org/W3134611008","https://openalex.org/W3197790422","https://openalex.org/W4225317694","https://openalex.org/W4302067267","https://openalex.org/W6712576390","https://openalex.org/W6745754512"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2787035864","https://openalex.org/W2373675101","https://openalex.org/W2048014685","https://openalex.org/W2370972896","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948"],"abstract_inverted_index":{"Classification":[0],"of":[1,151,220],"normal":[2,194],"vs.":[3,195],"pathological":[4,196],"infant":[5,12,41,47,197,211],"cries":[6,198],"is":[7,201],"a":[8,110,148],"challenging":[9],"task":[10],"as":[11],"cry":[13,42,48,203,212],"has":[14],"higher":[15],"fundamental":[16],"(or":[17],"pitch)":[18],"frequency":[19],"$(F_{0})$":[20],"and":[21,60,84,87,134,154,159,174,179,199],"hence,":[22],"distantly-spaced":[23],"pitch":[24],"source":[25],"harmonics":[26],"that":[27,140,184],"sample":[28],"vocal":[29],"tract":[30],"spectrum":[31],"resulting":[32],"in":[33,114,120,214],"poor":[34],"spectral":[35],"resolution.":[36],"This":[37,182],"paper":[38],"first":[39],"presents":[40],"classification":[43,93,213],"system":[44],"on":[45,66,78,81,206],"DA-IICT":[46,85],"corpus":[49],"using":[50,131,157,168,177,227],"two":[51,101],"cepstral":[52],"features,":[53],"namely,":[54,69,128],"Mel":[55],"Frequency":[56],"Cepstral":[57,63],"Coefficients":[58,64],"(MFCC),":[59],"Constant-Q":[61],"Transform":[62],"(CQCC)":[65],"statistical":[67],"classifiers,":[68],"Gaussian":[70],"Mixture":[71],"Model":[72],"(GMM).":[73],"Results":[74],"are":[75,95,164,188,225],"then":[76],"presented":[77,97],"cross-dataset":[79],"scenarios":[80],"Baby":[82],"Chilanto":[83],"datasets":[86],"found":[88,106,165],"to":[89,107,166],"degrade":[90,108,167],"substantially.":[91],"The":[92,136],"results":[94,104,137,163],"also":[96],"by":[98,147,171],"merging":[99],"these":[100],"corpora,":[102],"where":[103],"were":[105],"for":[109,193,210],"certain":[111],"parameter":[112],"setting":[113],"CQCC.":[115],"To":[116],"mitigate":[117],"this":[118],"degradation":[119],"performance,":[121],"we":[122],"present":[123],"three":[124],"data":[125],"augmentation":[126],"methods,":[127],"signal":[129],"perturbation":[130,143,170],"tempo,":[132],"volume,":[133],"speed.":[135],"obtained,":[138],"indicated":[139],"the":[141,145,215,218,221],"tempo":[142],"enhances":[144],"performance":[146,219],"small":[149],"margin":[150],"0.2":[152],"%":[153,156,173,176],"0.98":[155],"MFCC":[158,178],"CQCC,":[160,180],"respectively.":[161,181],"However,":[162],"speed":[169],"3.49":[172],"21.93":[175],"indicates":[183],"F0and":[185],"it\u2019s":[186],"dynamics":[187],"very":[189],"crucial":[190],"acoustic":[191],"cues":[192],"which":[200],"why":[202],"modes":[204],"based":[205],"F0were":[207],"used":[208],"historically":[209],"literature.":[216],"Additionally,":[217],"various":[222],"feature":[223],"sets":[224],"compared":[226],"J-statistics.":[228]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}