{"id":"https://openalex.org/W2405409871","doi":"https://doi.org/10.21437/eurospeech.2003-507","title":"Environmental sound source identification based on hidden Markov model for robust speech recognition","display_name":"Environmental sound source identification based on hidden Markov model for robust speech recognition","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W2405409871","doi":"https://doi.org/10.21437/eurospeech.2003-507","mag":"2405409871"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-507","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-507","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://naist.repo.nii.ac.jp/records/4531","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009257831","display_name":"Takanobu Nishiura","orcid":"https://orcid.org/0000-0002-1706-4743"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Takanobu Nishiura","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004029103","display_name":"Kazuhiro Miki","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazuhiro Miki","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5021868389","display_name":"Kiyohiro Shikano","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kiyohiro Shikano","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5009257831"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8889,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.7741662,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2157","last_page":"2160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8481000065803528,"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":0.8481000065803528,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8092032074928284},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7118526101112366},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6928236484527588},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5820916295051575},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.45090028643608093},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4488737881183624},{"id":"https://openalex.org/keywords/environmental-noise","display_name":"Environmental noise","score":0.420623779296875},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4154842495918274},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3555941581726074},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.26428157091140747},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.21773427724838257},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.20221847295761108}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8092032074928284},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7118526101112366},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6928236484527588},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5820916295051575},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.45090028643608093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4488737881183624},{"id":"https://openalex.org/C86781634","wikidata":"https://www.wikidata.org/wiki/Q2478325","display_name":"Environmental noise","level":3,"score":0.420623779296875},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4154842495918274},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3555941581726074},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26428157091140747},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.21773427724838257},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.20221847295761108},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/eurospeech.2003-507","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-507","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005782982","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4531","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005782982","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4531","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"conference paper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1521297879","https://openalex.org/W2036150633","https://openalex.org/W3184123547","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W2536059291"],"abstract_inverted_index":{"In":[0],"real":[1],"acoustic":[2,59],"environments,":[3],"humans":[4],"communicate":[5,62],"with":[6,63,145],"each":[7],"other":[8,28],"through":[9],"speech":[10,16,33,40,111,124,146,162],"by":[11,82],"focusing":[12],"on":[13],"the":[14,24,35,38,58,130,136,141,160],"target":[15,25,39,161],"among":[17],"environmental":[18,29,42,74,93,118,122],"sounds.":[19,30,94],"We":[20],"can":[21],"easily":[22],"identify":[23],"sound":[26,75],"from":[27,41],"For":[31],"hands-free":[32],"recognition,":[34],"identification":[36,96],"of":[37,85,92,116,129],"sounds":[43,79,119],"is":[44],"imperative.":[45],"This":[46,100],"mechanism":[47],"may":[48],"also":[49,102],"be":[50],"important":[51],"for":[52,120],"a":[53,104,127,149,164],"self-moving":[54],"robot":[55],"to":[56,159],"sense":[57],"environments":[60],"and":[61,87,113,148],"humans.":[64],"Therefore,":[65],"this":[66],"paper":[67,101],"first":[68],"proposes":[69,103],"Hidden":[70],"Markov":[71],"Model":[72],"(HMM)-based":[73],"source":[76],"identification.":[77],"Environmental":[78],"are":[80],"modeled":[81],"three":[83],"states":[84],"HMMs":[86,112,147],"evaluated":[88],"using":[89,155],"92":[90],"kinds":[91],"The":[95],"accuracy":[97],"was":[98],"95.4%.":[99],"new":[105],"HMM":[106,115,138,143,153],"composition":[107,139,144],"method":[108],"that":[109,135],"composes":[110],"an":[114],"categorized":[117],"robust":[121],"sound-added":[123],"recognition.":[125],"As":[126],"result":[128],"evaluation":[131],"experiments,":[132],"we":[133],"confirmed":[134],"proposed":[137],"outperforms":[140],"conventional":[142],"noise":[150,156],"(environmental":[151],"sound)":[152],"trained":[154],"periods":[157],"prior":[158],"in":[163],"captured":[165],"signal.":[166]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}