{"id":"https://openalex.org/W1505896651","doi":"https://doi.org/10.1109/icdsp.2015.7251908","title":"Subband spectral histogram feature for improved sound recognition in low SNR conditions","display_name":"Subband spectral histogram feature for improved sound recognition in low SNR conditions","publication_year":2015,"publication_date":"2015-07-01","ids":{"openalex":"https://openalex.org/W1505896651","doi":"https://doi.org/10.1109/icdsp.2015.7251908","mag":"1505896651"},"language":"en","primary_location":{"id":"doi:10.1109/icdsp.2015.7251908","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdsp.2015.7251908","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":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.02046409,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"432","last_page":"435"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9237609505653381},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.8593769073486328},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.7244095802307129},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6895394325256348},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6510934233665466},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.568411111831665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5214816331863403},{"id":"https://openalex.org/keywords/histogram-matching","display_name":"Histogram matching","score":0.43891671299934387},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39348652958869934},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32245534658432007},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.24809113144874573}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9237609505653381},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.8593769073486328},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.7244095802307129},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6895394325256348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6510934233665466},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.568411111831665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5214816331863403},{"id":"https://openalex.org/C127449775","wikidata":"https://www.wikidata.org/wiki/Q3785871","display_name":"Histogram matching","level":4,"score":0.43891671299934387},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39348652958869934},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32245534658432007},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.24809113144874573},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdsp.2015.7251908","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdsp.2015.7251908","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":12,"referenced_works":["https://openalex.org/W1965098113","https://openalex.org/W1974387177","https://openalex.org/W2090431713","https://openalex.org/W2109779985","https://openalex.org/W2125610452","https://openalex.org/W2135070170","https://openalex.org/W2148603752","https://openalex.org/W2154664200","https://openalex.org/W2171000037","https://openalex.org/W2245569228","https://openalex.org/W2312381234","https://openalex.org/W6690610466"],"related_works":["https://openalex.org/W2794704245","https://openalex.org/W1998334300","https://openalex.org/W2247097764","https://openalex.org/W2066185872","https://openalex.org/W2375849557","https://openalex.org/W2110241600","https://openalex.org/W2146297113","https://openalex.org/W2109325523","https://openalex.org/W2324508068","https://openalex.org/W2141966243"],"abstract_inverted_index":{"In":[0,114],"this":[1,37],"work,":[2,94],"we":[3,40,57,66,79],"use":[4],"the":[5,12,20,42,46,60,68,71,82,95,116,123,126],"subband":[6],"intensity":[7],"histogram":[8,43,62,75,84],"values":[9],"extracted":[10],"from":[11,45,92],"spectrogram":[13,51,72],"image":[14,52,73],"of":[15,53,129],"sound":[16,24,54],"signals":[17],"to":[18,70,89,99],"form":[19],"feature":[21,63,76,85,132],"vector":[22],"for":[23],"classification":[25,112],"in":[26,104],"an":[27],"audio":[28],"surveillance":[29],"application.":[30],"We":[31],"propose":[32],"two":[33],"features":[34,44,91],"based":[35],"on":[36],"approach.":[38],"Firstly,":[39],"extract":[41],"short":[47],"time":[48],"Fourier":[49],"transform":[50],"signals,":[55],"which":[56,78],"refer":[58,80],"as":[59,81],"spectral":[61],"(SHF).":[64],"Secondly,":[65],"apply":[67],"mel-filter":[69],"before":[74],"extraction":[77],"mel-spectral":[83],"(MSHF).":[86],"When":[87],"compared":[88],"baseline":[90],"similar":[93],"SHF":[96,124],"was":[97],"shown":[98],"give":[100],"significantly":[101],"improved":[102],"results":[103,121],"low":[105],"SNR":[106],"conditions":[107],"with":[108,125],"a":[109,130],"higher":[110],"overall":[111],"performance.":[113],"addition,":[115],"MSHF":[117],"produced":[118],"even":[119],"better":[120],"than":[122],"added":[127],"advantage":[128],"lower":[131],"dimension.":[133]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}