{"id":"https://openalex.org/W46241468","doi":"https://doi.org/10.21437/icslp.1998-303","title":"Coherence-based subband decomposition for robust speech and speaker recognition in noisy and reverberant rooms","display_name":"Coherence-based subband decomposition for robust speech and speaker recognition in noisy and reverberant rooms","publication_year":1998,"publication_date":"1998-11-30","ids":{"openalex":"https://openalex.org/W46241468","doi":"https://doi.org/10.21437/icslp.1998-303","mag":"46241468"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.1998-303","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","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/A5011964320","display_name":"Joaqu\u00edn Gonz\u00e1lez-Rodr\u00edguez","orcid":"https://orcid.org/0000-0003-0910-2575"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Joaquin Gonzalez-Rodriguez","raw_affiliation_strings":["Technical University Of Madrid"],"affiliations":[{"raw_affiliation_string":"Technical University Of Madrid","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047315770","display_name":"Santiago Cruz-Llanas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Santiago Cruz-Llanas","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078069400","display_name":"Javier Ortega-Garc\u00eda","orcid":"https://orcid.org/0000-0003-0557-1948"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Javier Ortega-Garc\u00eda","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011964320"],"corresponding_institution_ids":["https://openalex.org/I88060688"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.00702247,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"paper 0064","last_page":"0"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.7462063431739807},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7331767082214355},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7041376829147339},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.64243483543396},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5045362710952759},{"id":"https://openalex.org/keywords/broadband","display_name":"Broadband","score":0.5014908313751221},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.49954724311828613},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4292445480823517},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4215797185897827},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.37122833728790283},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2529352605342865},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.24953868985176086},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1697971224784851},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12628746032714844},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08839300274848938}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7462063431739807},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7331767082214355},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7041376829147339},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.64243483543396},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5045362710952759},{"id":"https://openalex.org/C509933004","wikidata":"https://www.wikidata.org/wiki/Q194163","display_name":"Broadband","level":2,"score":0.5014908313751221},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.49954724311828613},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4292445480823517},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4215797185897827},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.37122833728790283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2529352605342865},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.24953868985176086},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1697971224784851},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12628746032714844},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08839300274848938},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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":1,"locations":[{"id":"doi:10.21437/icslp.1998-303","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2060108923","https://openalex.org/W2066153957","https://openalex.org/W2088841593","https://openalex.org/W2099655464","https://openalex.org/W2117678320","https://openalex.org/W2120506807","https://openalex.org/W2121242659","https://openalex.org/W2131652765","https://openalex.org/W2154485269"],"related_works":["https://openalex.org/W1562475690","https://openalex.org/W1488529827","https://openalex.org/W4389082013","https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2380771148","https://openalex.org/W2900122540","https://openalex.org/W2396048001"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"the":[3,15,81,88,92,103],"acoustic":[4],"characteristics":[5],"of":[6,18,32,56,80,91,116],"sound":[7],"fields":[8],"in":[9,14,22,54,61,84,98,128],"enclosed":[10],"rooms":[11],"are":[12,46],"studied":[13],"joint":[16],"presence":[17],"speech":[19,42],"and":[20,37,48,65,131],"noise,":[21],"order":[23,85],"to":[24,50,86],"design":[25],"a":[26,62,73,123],"broadband":[27,74],"microphone":[28],"array":[29,44],"system":[30,53],"capable":[31],"coping":[33],"with":[34,122],"both":[35],"coherent":[36,117],"diffuse":[38,110],"noises.":[39,118],"Several":[40],"state-of-the-art":[41],"enhancement":[43],"structures":[45,139],"presented":[47],"compared":[49],"our":[51],"new":[52],"terms":[55],"correct":[57],"word":[58],"recognition":[59],"rates":[60],"simple":[63],"command":[64],"control":[66],"task.":[67],"The":[68,119],"proposed":[69],"structure,":[70],"based":[71],"on":[72],"subband-nested":[75],"array,":[76],"performs":[77],"real-time":[78],"estimations":[79],"spatial":[82],"coherence":[83],"determine":[87],"coherent/diffuse":[89],"nature":[90],"different":[93,96,129],"subbands,":[94],"using":[95],"filters":[97],"each":[99],"case,":[100],"improving":[101],"also":[102],"classical":[104],"Wiener":[105],"post-filter,":[106],"typically":[107],"used":[108],"for":[109,113],"noise":[111,132],"supression,":[112],"proper":[114],"cancellation":[115],"results":[120],"obtained":[121],"15-channel":[124],"simultaneous":[125],"recording":[126],"database":[127],"reverberation":[130],"conditions":[133],"show":[134],"better":[135],"performance":[136],"than":[137],"other":[138],"previously":[140],"proposed.":[141]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
