{"id":"https://openalex.org/W126265399","doi":"https://doi.org/10.21437/interspeech.2009-353","title":"Optimization of dereverberation parameters based on likelihood of speech recognizer","display_name":"Optimization of dereverberation parameters based on likelihood of speech recognizer","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W126265399","doi":"https://doi.org/10.21437/interspeech.2009-353","mag":"126265399"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-353","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-353","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},"type":"conference-paper","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/A5052470310","display_name":"Randy G\u00f3mez","orcid":"https://orcid.org/0000-0002-3191-6818"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Randy Gomez","raw_affiliation_strings":["Nara Institute of Science and Technology, Ikoma, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1223","last_page":"1226"},"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":0.9986000061035156,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.8040947914123535},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7901755571365356},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6888250112533569},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6333457827568054},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5748691558837891},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.4712287187576294},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4369615316390991},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2991464138031006},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25684040784835815},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.23483887314796448},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.11602988839149475},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0795694887638092}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8040947914123535},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7901755571365356},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6888250112533569},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6333457827568054},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5748691558837891},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.4712287187576294},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4369615316390991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2991464138031006},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25684040784835815},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.23483887314796448},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.11602988839149475},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0795694887638092},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2009-353","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-353","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.160.4957","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.160.4957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ar.media.kyoto-u.ac.jp/EN/bib/intl/GOM-EUROSP09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1585936487","https://openalex.org/W1963844140","https://openalex.org/W2009106392","https://openalex.org/W2053241019","https://openalex.org/W2104690216","https://openalex.org/W2104924374","https://openalex.org/W2106119541","https://openalex.org/W2132214945","https://openalex.org/W2141418660","https://openalex.org/W2147542668","https://openalex.org/W2151046798","https://openalex.org/W2970850616"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2022849831","https://openalex.org/W2037265366","https://openalex.org/W2026603686","https://openalex.org/W2331622705","https://openalex.org/W2391832549","https://openalex.org/W4401069787","https://openalex.org/W1499578372","https://openalex.org/W2368849850"],"abstract_inverted_index":{"Speech":[0],"recognition":[1,100],"under":[2],"reverberant":[3,19,87],"condition":[4],"is":[5,59,73],"a":[6],"difficult":[7],"task.":[8],"Most":[9],"dereverberation":[10,38,45],"techniques":[11],"used":[12],"to":[13,49],"address":[14],"this":[15,29],"problem":[16],"enhance":[17],"the":[18,25,33,44,51,54,79,94,99,103],"waveform":[20],"independent":[21],"from":[22],"that":[23,93],"of":[24,53,61,78],"speech":[26],"recognizer.":[27],"In":[28,40],"paper,":[30],"we":[31],"improve":[32,50],"conventional":[34,104],"Spectral":[35],"Subtraction-based":[36],"(SS)":[37],"technique.":[39],"our":[41],"proposed":[42,95],"approach,":[43],"parameters":[46,65],"are":[47],"optimized":[48],"likelihood":[52],"acoustic":[55,68],"model.":[56],"The":[57],"system":[58],"capable":[60],"adaptively":[62],"fine-tuning":[63],"these":[64],"jointly":[66],"with":[67],"model":[69],"training.":[70],"Additional":[71],"optimization":[72],"also":[74],"implemented":[75],"during":[76],"decoding":[77],"test":[80],"utterances.":[81],"We":[82],"have":[83],"evaluated":[84],"using":[85],"real":[86],"data":[88],"and":[89],"experimental":[90],"results":[91],"show":[92],"method":[96],"significantly":[97],"improves":[98],"performance":[101],"over":[102],"approach.":[105]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}