{"id":"https://openalex.org/W1552371796","doi":"https://doi.org/10.1109/icdsp.2015.7251910","title":"Cochleagram image feature for improved robustness in sound recognition","display_name":"Cochleagram image feature for improved robustness in sound recognition","publication_year":2015,"publication_date":"2015-07-01","ids":{"openalex":"https://openalex.org/W1552371796","doi":"https://doi.org/10.1109/icdsp.2015.7251910","mag":"1552371796"},"language":"en","primary_location":{"id":"doi:10.1109/icdsp.2015.7251910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdsp.2015.7251910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Digital Signal Processing (DSP)","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/A5023279352","display_name":"Roneel V. Sharan","orcid":"https://orcid.org/0000-0003-1079-8709"},"institutions":[{"id":"https://openalex.org/I39854758","display_name":"Auckland University of Technology","ror":"https://ror.org/01zvqw119","country_code":"NZ","type":"education","lineage":["https://openalex.org/I39854758"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Roneel V. Sharan","raw_affiliation_strings":["School of Engineering, Auckland University of Technology, Auckland, New Zealand","School of Engineering, Auckland University of Technology, Private Bag 92006, 1142, New Zealand"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Auckland University of Technology, Auckland, New Zealand","institution_ids":["https://openalex.org/I39854758"]},{"raw_affiliation_string":"School of Engineering, Auckland University of Technology, Private Bag 92006, 1142, New Zealand","institution_ids":["https://openalex.org/I39854758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044116630","display_name":"T.J. Moir","orcid":"https://orcid.org/0000-0002-4291-6143"},"institutions":[{"id":"https://openalex.org/I39854758","display_name":"Auckland University of Technology","ror":"https://ror.org/01zvqw119","country_code":"NZ","type":"education","lineage":["https://openalex.org/I39854758"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Tom J. Moir","raw_affiliation_strings":["School of Engineering, Auckland University of Technology, Auckland, New Zealand","School of Engineering, Auckland University of Technology, Private Bag 92006, 1142, New Zealand"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Auckland University of Technology, Auckland, New Zealand","institution_ids":["https://openalex.org/I39854758"]},{"raw_affiliation_string":"School of Engineering, Auckland University of Technology, Private Bag 92006, 1142, New Zealand","institution_ids":["https://openalex.org/I39854758"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5023279352"],"corresponding_institution_ids":["https://openalex.org/I39854758"],"apc_list":null,"apc_paid":null,"fwci":2.0102,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.86525567,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"441","last_page":"444"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/spectrogram","display_name":"Spectrogram","score":0.9225893616676331},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.7338765263557434},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7089453339576721},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6894826292991638},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.629775881767273},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5981987118721008},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4867989718914032},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4626752734184265},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4580402076244354},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4530304968357086},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.4413795471191406},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.43292033672332764},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.34124863147735596}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9225893616676331},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.7338765263557434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7089453339576721},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6894826292991638},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.629775881767273},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5981987118721008},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4867989718914032},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4626752734184265},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4580402076244354},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4530304968357086},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.4413795471191406},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.43292033672332764},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34124863147735596},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdsp.2015.7251910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdsp.2015.7251910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Digital Signal Processing (DSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W144360651","https://openalex.org/W151849828","https://openalex.org/W396690109","https://openalex.org/W1489184006","https://openalex.org/W1965098113","https://openalex.org/W1974387177","https://openalex.org/W1978274651","https://openalex.org/W2037976268","https://openalex.org/W2050758723","https://openalex.org/W2057200980","https://openalex.org/W2090211080","https://openalex.org/W2090431713","https://openalex.org/W2148603752","https://openalex.org/W2245569228","https://openalex.org/W2294745040","https://openalex.org/W4233392025","https://openalex.org/W6605808725","https://openalex.org/W6606101944","https://openalex.org/W6613520308","https://openalex.org/W6690610466","https://openalex.org/W6697247452"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W2011227383","https://openalex.org/W2065606036","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W3179495260","https://openalex.org/W1996690921"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"use":[4],"the":[5,19,39,43,56,67,71,77,94],"cochleagram":[6,72,78],"image":[7,79],"of":[8,18,70],"sound":[9],"signals":[10],"for":[11],"time-frequency":[12],"analysis":[13],"and":[14,55,63,82,113],"feature":[15,90,111],"extraction,":[16],"instead":[17],"conventional":[20],"spectrogram":[21,118],"image,":[22],"in":[23,42,58,99],"an":[24],"audio":[25],"surveillance":[26],"application.":[27],"The":[28,46,120],"signal":[29,48],"is":[30,49,61],"firstly":[31],"passed":[32],"through":[33],"a":[34],"gammatone":[35],"filter":[36],"which":[37,65],"models":[38],"auditory":[40],"filters":[41],"human":[44],"cochlea.":[45],"filtered":[47],"then":[50,75],"divided":[51],"into":[52,80],"small":[53],"windows":[54],"energy":[57],"each":[59],"window":[60],"added":[62],"normalized":[64],"gives":[66],"intensity":[68],"values":[69],"image.":[73],"We":[74],"divide":[76],"blocks":[81],"extract":[83],"central":[84],"moments":[85],"as":[86],"features.":[87],"Using":[88],"two":[89],"vector":[91],"representation":[92,114],"methods,":[93],"results":[95,106,123],"show":[96],"significant":[97],"improvement":[98],"overall":[100],"classification":[101],"accuracy":[102],"when":[103],"compared":[104],"to":[105],"from":[107],"literature":[108],"employing":[109],"similar":[110],"extraction":[112],"techniques":[115],"but":[116],"using":[117],"images.":[119],"most":[121],"improved":[122],"were":[124],"at":[125],"low":[126],"signal-to-noise":[127],"ratios.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}