{"id":"https://openalex.org/W1586314988","doi":"https://doi.org/10.21437/interspeech.2008-436","title":"Hilbert envelope based spectro-temporal features for phoneme recognition in telephone speech","display_name":"Hilbert envelope based spectro-temporal features for phoneme recognition in telephone speech","publication_year":2008,"publication_date":"2008-09-22","ids":{"openalex":"https://openalex.org/W1586314988","doi":"https://doi.org/10.21437/interspeech.2008-436","mag":"1586314988"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2008-436","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-436","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":true,"oa_status":"green","oa_url":"http://publications.idiap.ch/index.php/publications/showcite/tsamuel:rr08-18","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"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":"Samuel Thomas","raw_affiliation_strings":["IDIAP research institute"],"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002536077","display_name":"Sriram Ganapathy","orcid":"https://orcid.org/0000-0002-5779-9066"},"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":"Sriram Ganapathy","raw_affiliation_strings":["IDIAP research institute"],"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042260050","display_name":"Hynek He\u0159mansk\u00fd","orcid":"https://orcid.org/0000-0001-8032-4811"},"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":"Hynek Hermansky","raw_affiliation_strings":["IDIAP research institute"],"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101787514"],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":2.3463,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.89357567,"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":"1521","last_page":"1524"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/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/speech-recognition","display_name":"Speech recognition","score":0.7628101110458374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6931434273719788},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6576954126358032},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5975184440612793},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.5564454793930054},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.47281232476234436},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.46405163407325745},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4338940978050232},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4000508189201355}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7628101110458374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6931434273719788},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6576954126358032},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5975184440612793},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.5564454793930054},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.47281232476234436},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.46405163407325745},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4338940978050232},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4000508189201355},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2008-436","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-436","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"},{"id":"pmh:oai:infoscience.tind.io:146313","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146313","pdf_url":"http://publications.idiap.ch/index.php/publications/showcite/tsamuel:rr08-18","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":"http://infoscience.epfl.ch/record/146313","raw_type":"Text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.172.4263","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.172.4263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.idiap.ch/ftp/reports/2008/tsamuel-idiap-rr-08-18.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.227.1559","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.227.1559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.clsp.jhu.edu/%7Esamuel/pdfs/htimit_fdlp.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.360.4263","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.360.4263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.idiap.ch/ftp/papers/2008/tsamuel-interspeech-2-2008.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:146313","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146313","pdf_url":"http://publications.idiap.ch/index.php/publications/showcite/tsamuel:rr08-18","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":"http://infoscience.epfl.ch/record/146313","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1586314988.pdf","grobid_xml":"https://content.openalex.org/works/W1586314988.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W157872538","https://openalex.org/W1553004968","https://openalex.org/W1570910243","https://openalex.org/W1771175131","https://openalex.org/W1966264494","https://openalex.org/W2050364914","https://openalex.org/W2075012882","https://openalex.org/W2090861223","https://openalex.org/W2096215262","https://openalex.org/W2101596234","https://openalex.org/W2103372210","https://openalex.org/W2109622017","https://openalex.org/W2137075158","https://openalex.org/W2148154194","https://openalex.org/W2150021272","https://openalex.org/W2162125266"],"related_works":["https://openalex.org/W2103741268","https://openalex.org/W2770593030","https://openalex.org/W3154990682","https://openalex.org/W2560201613","https://openalex.org/W1547679904","https://openalex.org/W2171975302","https://openalex.org/W1996690921","https://openalex.org/W78087358","https://openalex.org/W2155010696","https://openalex.org/W1677682992"],"abstract_inverted_index":{"Abstract.":[0],"In":[1,84],"this":[2,146],"paper,":[3,147],"we":[4,148],"present":[5,149],"a":[6,80,150],"spectro-temporal":[7,151],"feature":[8,106,131,152],"extraction":[9,153],"technique":[10,154],"using":[11,29,155,173],"sub-band":[12,42,98,156,186],"Hilbert":[13,22,43,157,166,187],"envelopes":[14,23,44,58,100,158,167,188],"of":[15,19,24,90,136,159,163,168],"relatively":[16,160],"long":[17,161],"segments":[18,162],"speech":[20,113,164],"signal.":[21,165],"the":[25,41,49,56,68,76,88,91,97,115,123,169,185,193],"sub-bands":[26,170],"are":[27,37,52,64,73,101,171,181,196],"estimated":[28,172],"Frequency":[30,174],"Domain":[31,175],"Linear":[32,176],"Prediction":[33,177],"(FDLP).":[34,178],"Spectral":[35,179],"features":[36,51,78,93,125,180,195],"derived":[38,182],"by":[39,54,183,198],"integrating":[40,184],"in":[45,114,139,189],"short-term":[46,190],"frames":[47,191],"and":[48,72,192],"temporal":[50,99,194],"formed":[53,197],"converting":[55,199],"FDLP":[57],"into":[59],"modulation":[60],"frequency":[61],"components.":[62],"These":[63],"then":[65],"combined":[66],"at":[67],"phoneme":[69,81,140],"posterior":[70],"level":[71],"used":[74],"as":[75],"input":[77],"for":[79,122],"recognition":[82,109],"system.":[83],"order":[85],"to":[86,94,105,128],"improve":[87],"robustness":[89],"proposed":[92,124],"telephone":[95,112],"speech,":[96],"gain":[102],"normalized":[103],"prior":[104],"extraction.":[107],"Phoneme":[108],"experiments":[110],"on":[111],"HTIMIT":[116],"database":[117],"show":[118],"significant":[119],"performance":[120],"improvements":[121],"when":[126],"compared":[127],"other":[129],"robust":[130],"techniques":[132],"(average":[133],"relative":[134],"reduction":[135],"11":[137],"%":[138],"error":[141],"rate).2":[142],"IDIAP\u2013RR":[143],"08-18":[144],"n":[145]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
