{"id":"https://openalex.org/W1599463166","doi":"https://doi.org/10.21437/interspeech.2008-287","title":"Front-end for far-field speech recognition based on frequency domain linear prediction","display_name":"Front-end for far-field speech recognition based on frequency domain linear prediction","publication_year":2008,"publication_date":"2008-09-22","ids":{"openalex":"https://openalex.org/W1599463166","doi":"https://doi.org/10.21437/interspeech.2008-287","mag":"1599463166"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2008-287","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-287","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":"https://infoscience.epfl.ch/record/146312/files/tsamuel-interspeech-1-2008.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"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":"middle","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":false,"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":"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/A5002536077"],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":1.5191,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81734654,"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":"984","last_page":"987"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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":0.9945999979972839,"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/computer-science","display_name":"Computer science","score":0.7119889259338379},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7078393697738647},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5941334962844849},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5299447774887085},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5242726802825928},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5191097259521484},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5068112015724182},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.49110934138298035},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.49009808897972107},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.47827041149139404},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4635104238986969},{"id":"https://openalex.org/keywords/impulse","display_name":"Impulse (physics)","score":0.4112505614757538},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3643651008605957},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3570406436920166},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.30116090178489685},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16380146145820618},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15111979842185974},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08552047610282898},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07504618167877197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7119889259338379},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7078393697738647},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5941334962844849},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5299447774887085},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5242726802825928},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5191097259521484},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5068112015724182},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.49110934138298035},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.49009808897972107},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.47827041149139404},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4635104238986969},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.4112505614757538},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3643651008605957},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3570406436920166},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.30116090178489685},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16380146145820618},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15111979842185974},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08552047610282898},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07504618167877197},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.21437/interspeech.2008-287","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-287","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:146312","is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/tsamuel:rr08-17","pdf_url":"https://infoscience.epfl.ch/record/146312/files/tsamuel-interspeech-1-2008.pdf","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/146312","raw_type":"Text"},{"id":"pmh:oai:infoscience.tind.io:146494","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146494","pdf_url":"http://publications.idiap.ch/downloads/reports/2008/tsamuel-idiap-rr-08-17.pdf","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"report"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.172.1180","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.172.1180","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-1-2008.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.172.1861","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.172.1861","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-08-17.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:146312","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146312","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.tind.io:146312","is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/tsamuel:rr08-17","pdf_url":"https://infoscience.epfl.ch/record/146312/files/tsamuel-interspeech-1-2008.pdf","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/146312","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1599463166.pdf","grobid_xml":"https://content.openalex.org/works/W1599463166.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1230632900","https://openalex.org/W1570910243","https://openalex.org/W1677682992","https://openalex.org/W1869334927","https://openalex.org/W1966264494","https://openalex.org/W2087170768","https://openalex.org/W2090861223","https://openalex.org/W2106314257","https://openalex.org/W2109622017","https://openalex.org/W2130432819","https://openalex.org/W2151484683","https://openalex.org/W2408660648","https://openalex.org/W4247773827"],"related_works":["https://openalex.org/W2363056088","https://openalex.org/W2987432963","https://openalex.org/W2053167664","https://openalex.org/W2780118011","https://openalex.org/W2079152323","https://openalex.org/W2598586350","https://openalex.org/W1979693044","https://openalex.org/W1999835922","https://openalex.org/W2145696007","https://openalex.org/W2186020725"],"abstract_inverted_index":{"Abstract.":[0],"Automatic":[1],"Speech":[2],"Recognition":[3],"(ASR)":[4],"systems":[5],"usually":[6],"fail":[7],"when":[8],"they":[9],"encounter":[10],"speech":[11,71,114],"from":[12],"far-field":[13,64,70,113],"microphone":[14],"in":[15,63,74,96,129],"reverberant":[16],"environments.":[17],"This":[18],"is":[19],"due":[20],"to":[21,58,78,105,134],"the":[22,34,86,107,118],"application":[23],"of":[24,69,99,126],"short-term":[25],"feature":[26,137],"extraction":[27,138],"techniques":[28],"which":[29,102],"do":[30],"not":[31],"compensate":[32],"for":[33],"artifacts":[35,61],"introduced":[36],"by":[37,117],"long":[38],"room":[39],"impulse":[40],"responses.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45],"propose":[46],"a":[47,97],"front-end,":[48],"based":[49],"on":[50,112],"Frequency":[51],"Domain":[52],"Linear":[53],"Prediction":[54],"(FDLP),":[55],"that":[56],"tries":[57],"remove":[59],"reverberation":[60],"present":[62],"speech.":[65],"Long":[66],"temporal":[67],"segments":[68],"are":[72,103],"analyzed":[73],"narrow":[75],"frequency":[76],"sub-bands":[77],"extract":[79],"FDLP":[80,93],"envelopes":[81],"and":[82],"residual":[83,87],"signals.":[84],"Filtering":[85],"signals":[88,101],"with":[89],"gain":[90],"normalized":[91],"inverse":[92],"filters":[94],"result":[95],"set":[98],"sub-band":[100],"synthesized":[104],"reconstruct":[106],"signal":[108],"back.":[109],"ASR":[110],"experiments":[111],"data":[115],"processed":[116],"proposed":[119],"front-end":[120],"show":[121],"significant":[122],"improvements":[123],"(relative":[124],"reduction":[125],"30":[127],"%":[128],"word":[130],"error":[131],"rate)":[132],"compared":[133],"other":[135],"robust":[136],"techniques.":[139],"2":[140],"IDIAP\u2013RR":[141],"08-17":[142],"1":[143]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
