{"id":"https://openalex.org/W197522488","doi":"https://doi.org/10.21437/interspeech.2007-638","title":"Advanced front-end for robust speech recognition in extremely adverse environments","display_name":"Advanced front-end for robust speech recognition in extremely adverse environments","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W197522488","doi":"https://doi.org/10.21437/interspeech.2007-638","mag":"197522488"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-638","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/123456789/31815","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115044944","display_name":"Dimitrios Dimitriadis","orcid":"https://orcid.org/0000-0001-8483-0105"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dimitrios Dimitriadis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000645757","display_name":"Jos\u00e9 C. Segura","orcid":"https://orcid.org/0000-0003-3746-0978"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jose C. Segura","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013746163","display_name":"Luz Garc\u00eda","orcid":"https://orcid.org/0000-0001-5904-5412"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luz Garcia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084949286","display_name":"Alexandros Potamianos","orcid":"https://orcid.org/0009-0007-1532-5288"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandros Potamianos","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106182541","display_name":"Petros Maragos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Petros Maragos","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5080570090","display_name":"Vassilis Pitsikalis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vassilis Pitsikalis","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5115044944"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6485,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66487045,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2425","last_page":"2428"},"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":0.9994999766349792,"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":0.9993000030517578,"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/normalization","display_name":"Normalization (sociology)","score":0.7711728811264038},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7269309759140015},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7107334136962891},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.674426257610321},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.620094895362854},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5354025363922119},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5011374950408936},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.47847649455070496},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4348198473453522},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4168532192707062},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4143398702144623},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3841095566749573},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14496812224388123}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7711728811264038},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7269309759140015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7107334136962891},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.674426257610321},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.620094895362854},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5354025363922119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5011374950408936},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.47847649455070496},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4348198473453522},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4168532192707062},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4143398702144623},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3841095566749573},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14496812224388123},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2007-638","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.4790","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.4790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sirio.ugr.es/segura/pdfdocs/DMSP_HAFE_ASR_Interspeech07.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.499.9901","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.499.9901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.telecom.tuc.gr/~potam/preprints/conf/07_intespeech_HAFE.pdf","raw_type":"text"},{"id":"pmh:oai:dspace.lib.ntua.gr:123456789/31815","is_oa":true,"landing_page_url":"http://hdl.handle.net/123456789/31815","pdf_url":null,"source":{"id":"https://openalex.org/S4377196837","display_name":"DSpace - NTUA (National Technical University of Athens)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I174458059","host_organization_name":"National Technical University of Athens","host_organization_lineage":["https://openalex.org/I174458059"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:dspace.lib.ntua.gr:123456789/31815","is_oa":true,"landing_page_url":"http://hdl.handle.net/123456789/31815","pdf_url":null,"source":{"id":"https://openalex.org/S4377196837","display_name":"DSpace - NTUA (National Technical University of Athens)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I174458059","host_organization_name":"National Technical University of Athens","host_organization_lineage":["https://openalex.org/I174458059"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W1968939597","https://openalex.org/W2014893602","https://openalex.org/W2073955790","https://openalex.org/W2074953333","https://openalex.org/W2114537326","https://openalex.org/W2115717467","https://openalex.org/W2120245324","https://openalex.org/W2145739261","https://openalex.org/W2148154194","https://openalex.org/W2152175514","https://openalex.org/W2163669870"],"related_works":["https://openalex.org/W203970584","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W284174822","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805"],"abstract_inverted_index":{"In":[0,59],"this":[1,60],"paper,":[2],"a":[3,67,134],"unified":[4],"approach":[5],"to":[6,46,109,133],"speech":[7,15,50,124],"enhancement,":[8,125],"feature":[9,12,93,115,127,130],"extraction":[10,94,116,128],"and":[11,70,102,129],"normalization":[13,131],"for":[14,142],"recognition":[16,51,57],"in":[17,39,52,66],"adverse":[18,111],"recording":[19],"conditions":[20],"is":[21,74,107],"presented.":[22],"The":[23,104],"proposed":[24,78],"frontend":[25],"system":[26],"consists":[27],"of":[28,35,49],"several":[29],"different,":[30],"independent,":[31],"processing":[32],"modules.":[33],"Each":[34],"the":[36,47,56,77,85],"algorithms":[37,63],"contained":[38],"these":[40,62],"modules":[41],"has":[42],"been":[43],"independently":[44],"applied":[45,108],"problem":[48],"noise,":[53],"significantly":[54],"improving":[55],"rates.":[58],"work,":[61],"are":[64],"merged":[65],"single":[68],"front-end":[69,80,106],"their":[71],"combined":[72],"performance":[73],"demonstrated.":[75],"Specifically,":[76],"advanced":[79,105],"extracts":[81],"noise-invariant":[82],"features":[83],"via":[84],"following":[86],"modules:":[87],"Wiener":[88],"filtering,":[89],"voice-activity":[90],"detection,":[91],"robust":[92,126],"(nonlinear":[95],"modulation":[96],"or":[97],"fractal":[98],"features),":[99],"parameter":[100],"equalization":[101],"frame-dropping.":[103],"extremely":[110],"environments":[112],"where":[113],"most":[114],"schemes":[117],"fail.":[118],"We":[119],"show":[120],"that":[121],"by":[122],"combining":[123],"up":[132],"fivefold":[135],"error":[136],"rate":[137],"reduction":[138],"can":[139],"be":[140],"achieved":[141],"certain":[143],"tasks.":[144]},"counts_by_year":[{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
