{"id":"https://openalex.org/W2116855220","doi":"https://doi.org/10.1109/icassp.2005.1415148","title":"HMM/ANN Based Spectral Peak Location Estimation for Noise Robust Speech Recognition","display_name":"HMM/ANN Based Spectral Peak Location Estimation for Noise Robust Speech Recognition","publication_year":2006,"publication_date":"2006-10-11","ids":{"openalex":"https://openalex.org/W2116855220","doi":"https://doi.org/10.1109/icassp.2005.1415148","mag":"2116855220"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1415148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/83111","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053319645","display_name":"Shajith Ikbal","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"S. Ikbal","raw_affiliation_strings":["IDIAP Research Institute, Martigny, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"IDIAP Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108291827","display_name":"H. Bourlard","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"H. Bourlard","raw_affiliation_strings":["IDIAP Research Institute, Martigny, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"IDIAP Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043551083","display_name":"Mathew Magimai.-Doss","orcid":"https://orcid.org/0000-0002-8714-1409"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"M. Magimai-Doss","raw_affiliation_strings":["IDIAP Research Institute, Martigny, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"IDIAP Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053319645"],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.1701121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"453","last_page":"456"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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":0.8134365081787109},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6873656511306763},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6248248219490051},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5992401242256165},{"id":"https://openalex.org/keywords/autocorrelation","display_name":"Autocorrelation","score":0.5974317193031311},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.581123411655426},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5372756719589233},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5132350921630859},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5082247257232666},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.5053666234016418},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43812116980552673},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.31017014384269714},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.1413571834564209},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10964179039001465}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8134365081787109},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6873656511306763},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6248248219490051},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5992401242256165},{"id":"https://openalex.org/C5297727","wikidata":"https://www.wikidata.org/wiki/Q786970","display_name":"Autocorrelation","level":2,"score":0.5974317193031311},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.581123411655426},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5372756719589233},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5132350921630859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5082247257232666},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.5053666234016418},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43812116980552673},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31017014384269714},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.1413571834564209},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10964179039001465},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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":2,"locations":[{"id":"doi:10.1109/icassp.2005.1415148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:83111","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/83111","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:83111","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/83111","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W130921173","https://openalex.org/W204308143","https://openalex.org/W1493299544","https://openalex.org/W1537192855","https://openalex.org/W1553004968","https://openalex.org/W1590728601","https://openalex.org/W1592386823","https://openalex.org/W2063666720","https://openalex.org/W2137075158","https://openalex.org/W2165712214","https://openalex.org/W2266266311","https://openalex.org/W4238354054","https://openalex.org/W4285719527","https://openalex.org/W6608245754","https://openalex.org/W6632891567","https://openalex.org/W6635408018"],"related_works":["https://openalex.org/W2140162372","https://openalex.org/W3008257843","https://openalex.org/W4378805784","https://openalex.org/W2963908655","https://openalex.org/W2546942002","https://openalex.org/W2539985974","https://openalex.org/W2970216048","https://openalex.org/W2065293157","https://openalex.org/W2382607599","https://openalex.org/W2171313699"],"abstract_inverted_index":{"In":[0],"this":[1,130],"paper,":[2],"we":[3],"present":[4],"an":[5,63,71],"HMM/ANN":[6],"based":[7],"algorithm":[8,16,61,87,131],"to":[9,40,125],"estimate":[10,53],"the":[11,25,29,45,55,60,67,85,91,101,108,133],"spectral":[12,117,121],"peak":[13,30,46,78],"locations.":[14,31],"This":[15],"makes":[17],"use":[18,34],"of":[19,35,54,73,77,84,93],"distinct":[20],"time-frequency":[21],"(TF)":[22],"patterns":[23,37],"in":[24,90],"spectrogram":[26],"for":[27,66,129],"estimating":[28],"Such":[32],"a":[33,51,74,94],"TF":[36],"is":[38,88],"expected":[39],"impose":[41],"temporal":[42],"constraints":[43],"during":[44],"estimation":[47,72],"task,":[48],"thereby":[49],"yielding":[50],"smoother":[52],"peaks":[56,118],"over":[57,80],"time.":[58,81],"Additionally,":[59],"uses":[62],"ergodic":[64],"topology":[65],"HMM/ANN,":[68],"thus":[69],"allowing":[70],"varying":[75],"number":[76],"locations":[79],"The":[82],"usefulness":[83],"proposed":[86],"evaluated":[89],"framework":[92],"recently":[95,109],"introduced":[96,110],"noise":[97],"robust":[98],"feature":[99],"called":[100],"spectro-temporal":[102],"activity":[103],"pattern":[104],"(STAP)":[105],"feature.":[106],"Interestingly,":[107],"phase":[111],"autocorrelation":[112],"(PAC)":[113],"spectrum,":[114],"with":[115],"enhanced":[116],"and":[119],"smoothed":[120],"valleys,":[122],"turns":[123],"out":[124],"be":[126],"more":[127],"appropriate":[128],"than":[132],"regular":[134],"spectrum.":[135]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}