{"id":"https://openalex.org/W2003206871","doi":"https://doi.org/10.1109/icassp.2010.5494888","title":"A psychoacoustic spectral subtraction method for noise suppression in automatic speech recognition","display_name":"A psychoacoustic spectral subtraction method for noise suppression in automatic speech recognition","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2003206871","doi":"https://doi.org/10.1109/icassp.2010.5494888","mag":"2003206871"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5494888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5494888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5027551410","display_name":"Serajul Haque","orcid":null},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Serajul Haque","raw_affiliation_strings":["School of Electrical, Electronic and Computer Engineering, University of Western Australia, Crawley, WA, Australia","School of Electrical, Electronic and Computer Engineering, University of Western Australia, 35 Stirling Highway, Crawley 6009, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical, Electronic and Computer Engineering, University of Western Australia, Crawley, WA, Australia","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"School of Electrical, Electronic and Computer Engineering, University of Western Australia, 35 Stirling Highway, Crawley 6009, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017213156","display_name":"Roberto Togneri","orcid":"https://orcid.org/0000-0002-3778-4633"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Roberto Togneri","raw_affiliation_strings":["School of Electrical, Electronic and Computer Engineering, University of Western Australia, Crawley, WA, Australia","School of Electrical, Electronic and Computer Engineering, University of Western Australia, 35 Stirling Highway, Crawley 6009, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical, Electronic and Computer Engineering, University of Western Australia, Crawley, WA, Australia","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"School of Electrical, Electronic and Computer Engineering, University of Western Australia, 35 Stirling Highway, Crawley 6009, Australia","institution_ids":["https://openalex.org/I177877127"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177877127"],"apc_list":null,"apc_paid":null,"fwci":0.3206,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.44318035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"7","issue":null,"first_page":"1618","last_page":"1621"},"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":0.9987000226974487,"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/psychoacoustics","display_name":"Psychoacoustics","score":0.7724523544311523},{"id":"https://openalex.org/keywords/critical-band","display_name":"Critical band","score":0.7583545446395874},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6961379051208496},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.62166428565979},{"id":"https://openalex.org/keywords/auditory-masking","display_name":"Auditory masking","score":0.5539860129356384},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.531633734703064},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.5288307070732117},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4750354588031769},{"id":"https://openalex.org/keywords/loudness","display_name":"Loudness","score":0.4449208676815033},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4420815408229828},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39250534772872925},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3514825701713562},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.34069597721099854},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.2200809121131897},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.16001206636428833},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.15814438462257385},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.14685261249542236}],"concepts":[{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.7724523544311523},{"id":"https://openalex.org/C96390635","wikidata":"https://www.wikidata.org/wiki/Q366708","display_name":"Critical band","level":2,"score":0.7583545446395874},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6961379051208496},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.62166428565979},{"id":"https://openalex.org/C77801330","wikidata":"https://www.wikidata.org/wiki/Q1363413","display_name":"Auditory masking","level":3,"score":0.5539860129356384},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.531633734703064},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.5288307070732117},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4750354588031769},{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.4449208676815033},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4420815408229828},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39250534772872925},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3514825701713562},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.34069597721099854},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2200809121131897},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.16001206636428833},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.15814438462257385},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.14685261249542236},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C85841341","wikidata":"https://www.wikidata.org/wiki/Q1135984","display_name":"Octave (electronics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2010.5494888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5494888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/80f1d9a2-8eb7-49d9-9ace-d58ec1adb5d1","is_oa":false,"landing_page_url":"https://research-repository.uwa.edu.au/en/publications/80f1d9a2-8eb7-49d9-9ace-d58ec1adb5d1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402523","display_name":"UWA Profiles and Research Repository (University of Western Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Haque, S & Togneri, R 2010, A Psychoacoustic Spectral Subtraction Method for Noise Suppression in Automatic Speech Recognition. in J H L Hansen (ed.), Proceedings of ICASSP2010. Dallas, Texas, USA edn, vol. CD Rom, IEEE, Institute of Electrical and Electronics Engineers, Dallas, USA, pp. 1618-1621, 35th International Conference on Acoustics, Speech, and Signal Processing, Dallas, Texas, United States, 14/03/10. https://doi.org/10.1109/ICASSP.2010.5494888","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1590447358","https://openalex.org/W1658344067","https://openalex.org/W2014098799","https://openalex.org/W2090861223","https://openalex.org/W2121973264","https://openalex.org/W2140419980","https://openalex.org/W2149535104","https://openalex.org/W2158185319","https://openalex.org/W2158336491","https://openalex.org/W2165071747","https://openalex.org/W3147539069","https://openalex.org/W6683325647"],"related_works":["https://openalex.org/W2393848477","https://openalex.org/W2892072280","https://openalex.org/W4237185157","https://openalex.org/W2996518094","https://openalex.org/W4378904787","https://openalex.org/W1515811937","https://openalex.org/W4239575149","https://openalex.org/W2365638398","https://openalex.org/W2917356541","https://openalex.org/W2070373320"],"abstract_inverted_index":{"A":[0],"time-frequency":[1],"spectral":[2,65,73,107],"subtraction":[3,66,108],"method":[4,89],"based":[5],"on":[6],"the":[7,21,60],"knowledge":[8],"of":[9,13,38],"several":[10],"psychoacoustic":[11,55],"properties":[12],"human":[14,61],"perception":[15],"is":[16,49,75],"presented.":[17],"These":[18],"effects":[19],"are":[20],"critical":[22],"band":[23],"filtering,":[24],"synaptic":[25],"adaptation":[26],"which":[27],"also":[28],"introduces":[29],"temporal":[30],"forward":[31],"masking,":[32],"equal":[33],"loudness":[34],"preemphasis,":[35],"power":[36],"law":[37],"hearing,":[39],"and":[40,47,71,94],"simultaneous":[41],"masking":[42],"effect.":[43],"The":[44,64,88],"perceptual":[45],"speech":[46,79],"noise":[48,93,102],"estimated":[50],"separately":[51],"by":[52,77],"a":[53,68,72,78,83],"detailed":[54],"non-linear":[56],"transformation":[57],"undergoing":[58],"in":[59,99],"auditory":[62],"system.":[63],"using":[67,82],"over-subtraction":[69],"factor":[70],"floor":[74],"measured":[76],"recognition":[80,97],"front-end":[81],"continuous":[84],"density":[85],"HMM":[86],"recognizer.":[87],"shows":[90],"reduced":[91],"residual":[92],"improved":[95],"word":[96],"performance":[98],"broadband":[100],"Gaussian":[101],"conditions":[103],"compared":[104],"to":[105],"conventional":[106],"method.":[109]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-14T07:06:38.338062","created_date":"2025-10-10T00:00:00"}
