{"id":"https://openalex.org/W2131548063","doi":"https://doi.org/10.1109/isit.2011.6034260","title":"Combined waveform-cepstral representation for robust speech recognition","display_name":"Combined waveform-cepstral representation for robust speech recognition","publication_year":2011,"publication_date":"2011-07-01","ids":{"openalex":"https://openalex.org/W2131548063","doi":"https://doi.org/10.1109/isit.2011.6034260","mag":"2131548063"},"language":"en","primary_location":{"id":"doi:10.1109/isit.2011.6034260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2011.6034260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Symposium on Information Theory Proceedings","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/A5013615516","display_name":"Matthew Ager","orcid":null},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]},{"id":"https://openalex.org/I4210119896","display_name":"King's College School","ror":"https://ror.org/02bbqcn27","country_code":"GB","type":"education","lineage":["https://openalex.org/I4210119896"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Matthew Ager","raw_affiliation_strings":["Department of Mathematics, Kings College London, UK","Dept. of Mathematics, King's College, London ,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Kings College London, UK","institution_ids":["https://openalex.org/I183935753"]},{"raw_affiliation_string":"Dept. of Mathematics, King's College, London ,UK","institution_ids":["https://openalex.org/I4210119896","https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056805951","display_name":"Zoran Cvetkovi\u0107","orcid":"https://orcid.org/0000-0002-5128-5099"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zoran Cvetkovic","raw_affiliation_strings":["Department of Informatics, Kings College London, UK","Department of Informatics, King's College, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Kings College London, UK","institution_ids":["https://openalex.org/I183935753"]},{"raw_affiliation_string":"Department of Informatics, King's College, London, UK","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069770227","display_name":"Peter Sollich","orcid":"https://orcid.org/0000-0003-0169-7893"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]},{"id":"https://openalex.org/I4210119896","display_name":"King's College School","ror":"https://ror.org/02bbqcn27","country_code":"GB","type":"education","lineage":["https://openalex.org/I4210119896"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Sollich","raw_affiliation_strings":["Department of Mathematics, Kings College London, UK","Dept. of Mathematics, King's College, London ,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Kings College London, UK","institution_ids":["https://openalex.org/I183935753"]},{"raw_affiliation_string":"Dept. of Mathematics, King's College, London ,UK","institution_ids":["https://openalex.org/I4210119896","https://openalex.org/I183935753"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8793,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81170994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"119","issue":null,"first_page":"864","last_page":"868"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7272282838821411},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.7114563584327698},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6936618685722351},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.6864533424377441},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6565027832984924},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6134821772575378},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44057056307792664},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40180355310440063},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.27076882123947144},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06078672409057617}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7272282838821411},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7114563584327698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6936618685722351},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.6864533424377441},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6565027832984924},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6134821772575378},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44057056307792664},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40180355310440063},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27076882123947144},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06078672409057617},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/isit.2011.6034260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2011.6034260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Symposium on Information Theory Proceedings","raw_type":"proceedings-article"},{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/3f658a03-f22f-4417-bc41-4bac398ea19c","is_oa":false,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/3f658a03-f22f-4417-bc41-4bac398ea19c","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ager, M, Cvetkovic, Z & Sollich, P 2011, Combined Waveform-Cepstral Representation for Robust Speech Recognition. in Unknown. 2011 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY PROCEEDINGS (ISIT), NEW YORK, pp. 864 - 868, IEEE International Symposium on Information Theory (ISIT), St Petersburg, RUSSIA, 31/07/2011.","raw_type":"contributionToPeriodical"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3256636000","display_name":null,"funder_award_id":"EP/D053005/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1560013842","https://openalex.org/W1635512741","https://openalex.org/W1970533835","https://openalex.org/W1989932830","https://openalex.org/W1994396704","https://openalex.org/W2002342963","https://openalex.org/W2029401646","https://openalex.org/W2065866650","https://openalex.org/W2066561607","https://openalex.org/W2077804127","https://openalex.org/W2089935161","https://openalex.org/W2090861223","https://openalex.org/W2100567442","https://openalex.org/W2106554350","https://openalex.org/W2114827915","https://openalex.org/W2116217121","https://openalex.org/W2121594221","https://openalex.org/W2126597753","https://openalex.org/W2148154194","https://openalex.org/W2149497729","https://openalex.org/W2160620631","https://openalex.org/W2163680580","https://openalex.org/W2164597369","https://openalex.org/W2619993508","https://openalex.org/W6650992335","https://openalex.org/W6682073222"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W2038216521","https://openalex.org/W4385672897","https://openalex.org/W2736574136","https://openalex.org/W106160982","https://openalex.org/W894828327","https://openalex.org/W2136559180"],"abstract_inverted_index":{"High-dimensional":[0],"acoustic":[1,57,70],"waveform":[2,58],"representations":[3,29,59,88],"are":[4,30,46,60],"studied":[5],"as":[6],"a":[7],"front-end":[8],"for":[9],"noise":[10,54,91],"robust":[11,63],"automatic":[12],"speech":[13],"recognition":[14,40],"using":[15,48],"generative":[16],"methods,":[17],"in":[18],"particular":[19],"Gaussian":[20],"mixture":[21],"models":[22],"and":[23,39,72,78],"hidden":[24],"Markov":[25],"models.":[26],"The":[27],"proposed":[28],"compared":[31],"with":[32],"standard":[33],"cepstral":[34,49,73],"features":[35,50,74],"on":[36],"phoneme":[37],"classification":[38],"tasks.":[41],"While":[42],"lower":[43],"error":[44],"rates":[45],"achieved":[47],"at":[51],"very":[52],"low":[53],"levels,":[55],"the":[56,86],"much":[61],"more":[62],"to":[64],"noise.":[65],"A":[66],"convex":[67],"combination":[68],"of":[69,85],"waveforms":[71],"is":[75],"then":[76],"considered":[77],"it":[79],"achieves":[80],"higher":[81],"accuracy":[82],"than":[83],"either":[84],"individual":[87],"across":[89],"all":[90],"levels.":[92]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2013,"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"}