{"id":"https://openalex.org/W2160569100","doi":"https://doi.org/10.1109/asru.2007.4430093","title":"Design and implementation of a robot audition system for automatic speech recognition of simultaneous speech","display_name":"Design and implementation of a robot audition system for automatic speech recognition of simultaneous speech","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2160569100","doi":"https://doi.org/10.1109/asru.2007.4430093","mag":"2160569100"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2007.4430093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition &amp; Understanding (ASRU)","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/A5112288156","display_name":"Shun\u2019ichi Yamamoto","orcid":null},"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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shun'ichi Yamamoto","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091708408","display_name":"Kazuhiro Nakadai","orcid":"https://orcid.org/0000-0002-6134-4558"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Nakadai","raw_affiliation_strings":["Honda Research Institute Japan Company Limited, Wako, Saitama, Japan"],"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Company Limited, Wako, Saitama, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085401834","display_name":"Mikio Nakano","orcid":"https://orcid.org/0000-0001-6057-3132"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mikio Nakano","raw_affiliation_strings":["Honda Research Institute Japan Company Limited, Wako, Saitama, Japan"],"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Company Limited, Wako, Saitama, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008539902","display_name":"Hiroshi Tsujino","orcid":"https://orcid.org/0000-0001-8042-2796"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Tsujino","raw_affiliation_strings":["Honda Research Institute Japan Company Limited, Wako, Saitama, Japan"],"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Company Limited, Wako, Saitama, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021269794","display_name":"Jean-Marc Valin","orcid":"https://orcid.org/0000-0002-9883-6927"},"institutions":[{"id":"https://openalex.org/I4210128581","display_name":"Information and Communication Technologies Centre","ror":"https://ror.org/034x2fx50","country_code":"AU","type":"facility","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4210128581","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"funder","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jean-Marc Valin","raw_affiliation_strings":["CSIRO ICT Centre, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"CSIRO ICT Centre, NSW, Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I4210128581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049614400","display_name":"Kazunori Komatani","orcid":"https://orcid.org/0000-0002-6052-600X"},"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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazunori Komatani","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055922202","display_name":"Tetsuya Ogata","orcid":"https://orcid.org/0000-0001-7015-0379"},"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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Ogata","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005141184","display_name":"Hiroshi G. Okuno","orcid":"https://orcid.org/0000-0002-8704-4318"},"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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi G. Okuno","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5112288156"],"corresponding_institution_ids":["https://openalex.org/I22299242","https://openalex.org/I39012071"],"apc_list":null,"apc_paid":null,"fwci":2.2168,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.89143073,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"44","issue":null,"first_page":"111","last_page":"116"},"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":0.9987000226974487,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.8075522184371948},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7578592896461487},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7558927536010742},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7354555726051331},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5651527047157288},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5607457756996155},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5071947574615479},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5065346956253052},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4863281846046448},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4687236547470093},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4559805989265442},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.44954177737236023},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43397656083106995},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4134422540664673},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.41139906644821167},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.22517457604408264}],"concepts":[{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.8075522184371948},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7578592896461487},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7558927536010742},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7354555726051331},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5651527047157288},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5607457756996155},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5071947574615479},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5065346956253052},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4863281846046448},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4687236547470093},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4559805989265442},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.44954177737236023},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43397656083106995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4134422540664673},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.41139906644821167},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.22517457604408264},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2007.4430093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition &amp; Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5600000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W88587067","https://openalex.org/W289804034","https://openalex.org/W1487711593","https://openalex.org/W1823307876","https://openalex.org/W1888374534","https://openalex.org/W1996355918","https://openalex.org/W2026257980","https://openalex.org/W2049737414","https://openalex.org/W2074354966","https://openalex.org/W2099655464","https://openalex.org/W2121065047","https://openalex.org/W2121973264","https://openalex.org/W2126605958","https://openalex.org/W2126942983","https://openalex.org/W2134910060","https://openalex.org/W2136439176","https://openalex.org/W2146871184","https://openalex.org/W2147673046","https://openalex.org/W2148719987","https://openalex.org/W3147539069","https://openalex.org/W6603597747","https://openalex.org/W6610316520","https://openalex.org/W6678139903"],"related_works":["https://openalex.org/W2380771148","https://openalex.org/W2348931051","https://openalex.org/W2132495960","https://openalex.org/W2538903081","https://openalex.org/W2389562147","https://openalex.org/W4386746628","https://openalex.org/W2294333436","https://openalex.org/W2109356272","https://openalex.org/W2145603824","https://openalex.org/W4286233499"],"abstract_inverted_index":{"This":[0],"paper":[1,125],"addresses":[2],"robot":[3,103],"audition":[4,104],"that":[5,10],"can":[6],"cope":[7,25],"with":[8,26,43,69,120],"speech":[9,79,99,139],"has":[11],"a":[12,28,44,61],"low":[13],"signal-to-noise":[14],"ratio":[15],"(SNR)":[16],"in":[17,78,88],"real":[18],"time":[19],"by":[20,86,133],"using":[21,65,134],"robot-embedded":[22],"microphones.":[23],"To":[24],"such":[27],"noise,":[29],"we":[30],"exploited":[31],"two":[32,109,135],"key":[33,110],"ideas;":[34],"Preprocessing":[35,56],"consisting":[36],"of":[37,60,130],"sound":[38,63],"source":[39,67],"localization":[40],"and":[41,47,81,97,117,136],"separation":[42,68],"microphone":[45,122],"array,":[46],"system":[48,105],"integration":[49,94],"based":[50,106],"on":[51,107],"missing":[52],"feature":[53],"theory":[54],"(MFT).":[55],"improves":[57],"the":[58,128],"SNR":[59],"target":[62],"signal":[64],"geometric":[66],"multichannel":[70],"post-filter.":[71],"MFT":[72,90],"uses":[73],"only":[74],"reliable":[75],"acoustic":[76],"features":[77],"recognition":[80],"masks":[82],"unreliable":[83],"parts":[84],"caused":[85],"errors":[87],"preprocessing.":[89],"thus":[91],"provides":[92],"smooth":[93],"between":[95],"preprocessing":[96],"automatic":[98],"recognition.":[100],"A":[101],"real-time":[102],"these":[108],"ideas":[111],"is":[112],"constructed":[113],"for":[114],"Honda":[115],"ASIMO":[116],"Humanoid":[118],"SIG2":[119],"8-ch":[121],"arrays.":[123],"The":[124],"also":[126],"reports":[127],"improvement":[129],"ASR":[131],"performance":[132],"three":[137],"simultaneous":[138],"signals.":[140]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
