{"id":"https://openalex.org/W1648222827","doi":"https://doi.org/10.21437/interspeech.2008-208","title":"A closer look on hierarchical spectro-temporal features (HIST)","display_name":"A closer look on hierarchical spectro-temporal features (HIST)","publication_year":2008,"publication_date":"2008-09-22","ids":{"openalex":"https://openalex.org/W1648222827","doi":"https://doi.org/10.21437/interspeech.2008-208","mag":"1648222827"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2008-208","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","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/A5071842389","display_name":"Martin Heckmann","orcid":"https://orcid.org/0000-0002-1794-1160"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Martin Heckmann","raw_affiliation_strings":["Honda (Japan), Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda (Japan), Tokyo, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016992467","display_name":"Xavier Domont","orcid":null},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xavier Domont","raw_affiliation_strings":["Honda (Japan), Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda (Japan), Tokyo, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042767682","display_name":"Frank Joublin","orcid":"https://orcid.org/0000-0002-4421-1737"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Frank Joublin","raw_affiliation_strings":["Honda (Japan), Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda (Japan), Tokyo, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053974584","display_name":"Christian Goerick","orcid":null},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Christian Goerick","raw_affiliation_strings":["Honda (Japan), Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda (Japan), Tokyo, Japan","institution_ids":["https://openalex.org/I1283473643"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0419,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.90987292,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"894","last_page":"897"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7053505182266235},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6869907379150391},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6715283989906311},{"id":"https://openalex.org/keywords/receptive-field","display_name":"Receptive field","score":0.6678673028945923},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6628901958465576},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5564115643501282},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5347904562950134},{"id":"https://openalex.org/keywords/auditory-cortex","display_name":"Auditory cortex","score":0.48218217492103577},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.4696475863456726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4651675224304199},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4633252024650574},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43647122383117676},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.16752910614013672},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.07378384470939636}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7053505182266235},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6869907379150391},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6715283989906311},{"id":"https://openalex.org/C19071747","wikidata":"https://www.wikidata.org/wiki/Q1755207","display_name":"Receptive field","level":2,"score":0.6678673028945923},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6628901958465576},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5564115643501282},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5347904562950134},{"id":"https://openalex.org/C2780297895","wikidata":"https://www.wikidata.org/wiki/Q18676","display_name":"Auditory cortex","level":2,"score":0.48218217492103577},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.4696475863456726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4651675224304199},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4633252024650574},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43647122383117676},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.16752910614013672},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.07378384470939636},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2008-208","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W396690109","https://openalex.org/W1974387177","https://openalex.org/W2118718620","https://openalex.org/W2122832694","https://openalex.org/W2130426352","https://openalex.org/W2137075158","https://openalex.org/W2151484683","https://openalex.org/W2152131029","https://openalex.org/W2161224286","https://openalex.org/W2166676140","https://openalex.org/W2395865858"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W1967435588","https://openalex.org/W2545037074","https://openalex.org/W2396610872"],"abstract_inverted_index":{"Speech":[0],"recognition":[1,127,142],"robust":[2],"against":[3],"interfering":[4],"noise":[5],"remains":[6],"a":[7,13,97,115,124],"difficult":[8],"task.":[9,128],"We":[10],"previously":[11],"presented":[12],"set":[14,55],"of":[15,56,69,104,135],"spectrotemporal":[16],"speech":[17],"features":[18,25,139],"which":[19],"we":[20,95],"termed":[21],"Hierarchical":[22],"Spectro-Temporal":[23],"(HIST)":[24],"showing":[26],"improved":[27,141],"robustness,":[28],"especially":[29],"when":[30],"combined":[31,80],"with":[32],"RASTA-PLP.":[33],"They":[34],"are":[35,48,79],"inspired":[36],"by":[37],"the":[38,43,66,70,73,101,105,108,111,133],"receptive":[39,84],"fields":[40,85],"found":[41],"in":[42,50,144],"mammalian":[44],"auditory":[45],"cortex":[46],"and":[47,64,123,137],"organized":[49],"two":[51],"hierarchical":[52],"levels.":[53],"A":[54],"filters":[57],"learned":[58,86],"via":[59,87],"ICA":[60],"captures":[61],"local":[62,77],"variations":[63,78],"constitutes":[65],"first":[67],"layer":[68,75],"hierarchy.":[71],"In":[72,92],"second":[74],"these":[76],"to":[81,110],"form":[82],"larger":[83],"Non":[88],"Negative":[89],"Sparse":[90],"Coding.":[91],"this":[93],"paper":[94],"introduce":[96],"non-linear":[98],"smoothing":[99],"along":[100],"time":[102],"axis":[103],"spectrograms":[106],"at":[107],"input":[109],"hierarchy":[112],"and,":[113],"additionally,":[114],"more":[116],"thorough":[117],"performance":[118],"analysis":[119],"on":[120],"an":[121],"isolated":[122],"continuous":[125],"digit":[126],"The":[129],"results":[130],"show":[131],"that":[132],"combination":[134],"HIST":[136],"RASTA-PLP":[138],"yields":[140],"scores":[143],"noise.":[145]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}