{"id":"https://openalex.org/W1530136128","doi":"https://doi.org/10.21437/eurospeech.1999-568x","title":"Data collection in real acoustical environments for sound scene understanding and hands-free speech recognition","display_name":"Data collection in real acoustical environments for sound scene understanding and hands-free speech recognition","publication_year":1999,"publication_date":"1999-09-05","ids":{"openalex":"https://openalex.org/W1530136128","doi":"https://doi.org/10.21437/eurospeech.1999-568x","mag":"1530136128"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1999-568x","is_oa":true,"landing_page_url":"https://doi.org/10.21437/eurospeech.1999-568x","pdf_url":"https://www.isca-archive.org/eurospeech_1999/nakamura99x_eurospeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th European Conference on Speech Communication and Technology","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/eurospeech_1999/nakamura99x_eurospeech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056990370","display_name":"Kazuo Hiyane","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazuo Hiyane","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112430812","display_name":"Futoshi Asano","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Futoshi Asano","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073170587","display_name":"Takeshi Yamada","orcid":"https://orcid.org/0000-0002-5744-8469"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takeshi Yamada","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102765536","display_name":"Takashi Endo","orcid":"https://orcid.org/0000-0002-9857-1869"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takashi Endo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5020994673"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5197,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.73205932,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2255","last_page":"2258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8532000184059143,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8532000184059143,"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/T10860","display_name":"Speech and Audio Processing","score":0.843500018119812,"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/sound","display_name":"Sound (geography)","score":0.6596364378929138},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6288851499557495},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6156442761421204},{"id":"https://openalex.org/keywords/hands-free","display_name":"Hands free","score":0.5339310169219971},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.40446221828460693}],"concepts":[{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.6596364378929138},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6288851499557495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6156442761421204},{"id":"https://openalex.org/C3018339088","wikidata":"https://www.wikidata.org/wiki/Q28460","display_name":"Hands free","level":2,"score":0.5339310169219971},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.40446221828460693},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/eurospeech.1999-568x","is_oa":true,"landing_page_url":"https://doi.org/10.21437/eurospeech.1999-568x","pdf_url":"https://www.isca-archive.org/eurospeech_1999/nakamura99x_eurospeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th European Conference on Speech Communication and Technology","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005782969","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4518","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"},{"id":"pmh:oai:library.naist.jp:10061/7950","is_oa":true,"landing_page_url":"http://hdl.handle.net/10061/7950","pdf_url":"http://hdl.handle.net/10061/7950","source":{"id":"https://openalex.org/S4377196843","display_name":"NAIST Digital Library (Nara Institute of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I75917431","host_organization_name":"Nara Institute of Science and Technology","host_organization_lineage":["https://openalex.org/I75917431"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.21437/eurospeech.1999-568x","is_oa":true,"landing_page_url":"https://doi.org/10.21437/eurospeech.1999-568x","pdf_url":"https://www.isca-archive.org/eurospeech_1999/nakamura99x_eurospeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th European Conference on Speech Communication and Technology","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1530136128.pdf","grobid_xml":"https://content.openalex.org/works/W1530136128.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2909726438","https://openalex.org/W4396696052","https://openalex.org/W34077297"],"abstract_inverted_index":{"This":[0],"paper":[1,27],"describes":[2],"a":[3,30,148,165],"sound":[4,12,15,17,36,49,54,59,75,93,109,131,143,152,178],"scene":[5,37,55,94,153,179],"database":[6,95,180],"necessary":[7],"for":[8,32],"studies":[9],"such":[10],"as":[11],"source":[13,77],"localization,":[14],"retrieval,":[16],"recognition":[18,22],"and":[19,61,79,117,145,174],"hands-free":[20],"speech":[21,118],"in":[23,51,83,96,127,132,155],"real":[24,52,84,156],"acoustical":[25,85,129,157],"environments.This":[26],"reports":[28],"on":[29],"project":[31,181],"collection":[33],"of":[34,48,73,100,111,114,140,176],"the":[35,74,92,97,101,133,141,151,172],"data":[38,154],"supported":[39],"by":[40,58,138],"Real":[41],"World":[42],"Computing":[43],"Partnership(RWCP).There":[44],"are":[45,88,182],"many":[46,112],"kinds":[47,113],"scenes":[50],"environments.The":[53,130],"is":[56,81,105,122,159],"denoted":[57],"sources":[60,110,144],"room":[62],"acoustics.The":[63],"numb":[64],"e":[65],"r":[66],"o":[67,70],"f":[68],"c":[69],"m":[71],"bination":[72],"sources,":[76],"positions":[78],"rooms":[80],"huge":[82],"environments.Two":[86],"approaches":[87],"taken":[89],"to":[90,106,123,161],"build":[91],"early":[98],"stage":[99],"project.The":[102],"rst":[103],"approach":[104,121],"collect":[107,124],"isolated":[108,142],"non-speech":[115],"sounds":[116],"sounds.The":[119],"second":[120],"impulse":[125,146],"responses":[126],"various":[128],"environments":[134,158],"can":[135],"be":[136,162],"simulated":[137],"convolution":[139],"responses.In":[147],"later":[149],"stage,":[150],"planned":[160],"collected":[163],"using":[164],"three":[166],"dimensional":[167],"microphone":[168],"array.In":[169],"this":[170],"paper,":[171],"plan":[173],"progress":[175],"our":[177],"described.1.":[183]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}