{"id":"https://openalex.org/W1969796471","doi":"https://doi.org/10.1109/iros.2010.5651078","title":"Exploiting harmonic structures to improve separating simultaneous speech in under-determined conditions","display_name":"Exploiting harmonic structures to improve separating simultaneous speech in under-determined conditions","publication_year":2010,"publication_date":"2010-10-01","ids":{"openalex":"https://openalex.org/W1969796471","doi":"https://doi.org/10.1109/iros.2010.5651078","mag":"1969796471"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2010.5651078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2010.5651078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE/RSJ International Conference on Intelligent Robots and Systems","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/A5037947046","display_name":"Yasusuke Hirasawa","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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Y Hirasawa","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","Graduate School of Informatics, Kyoto University, Sakyo, 606-8501, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo, 606-8501, JAPAN","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038310819","display_name":"Tohru Takahashi","orcid":"https://orcid.org/0000-0002-1130-0549"},"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":"T Takahashi","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","Graduate School of Informatics, Kyoto University, Sakyo, 606-8501, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo, 606-8501, JAPAN","institution_ids":["https://openalex.org/I22299242"]}]},{"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K Komatani","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","Graduate School of Informatics, Kyoto University, Sakyo, 606-8501, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo, 606-8501, JAPAN","institution_ids":["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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T Ogata","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","Graduate School of Informatics, Kyoto University, Sakyo, 606-8501, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo, 606-8501, JAPAN","institution_ids":["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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"H G Okuno","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","Graduate School of Informatics, Kyoto University, Sakyo, 606-8501, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo, 606-8501, JAPAN","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06270648,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"450","last_page":"457"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9994000196456909,"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":0.9990000128746033,"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/computer-science","display_name":"Computer science","score":0.6963413953781128},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6679009199142456},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6453403830528259},{"id":"https://openalex.org/keywords/anechoic-chamber","display_name":"Anechoic chamber","score":0.6069460511207581},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5760601758956909},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5470212697982788},{"id":"https://openalex.org/keywords/impulse","display_name":"Impulse (physics)","score":0.543677031993866},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.5221540927886963},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4712527096271515},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.45369675755500793},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.4284783601760864},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.41949188709259033},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4152686297893524},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.349536657333374},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1976718306541443},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19488605856895447},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.09598740935325623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6963413953781128},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6679009199142456},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6453403830528259},{"id":"https://openalex.org/C149712133","wikidata":"https://www.wikidata.org/wiki/Q332774","display_name":"Anechoic chamber","level":2,"score":0.6069460511207581},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5760601758956909},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5470212697982788},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.543677031993866},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.5221540927886963},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4712527096271515},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.45369675755500793},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.4284783601760864},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.41949188709259033},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4152686297893524},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.349536657333374},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1976718306541443},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19488605856895447},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.09598740935325623},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros.2010.5651078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2010.5651078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.174.9247","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.174.9247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://winnie.kuis.kyoto-u.ac.jp/members/okuno/Public/IROS2010-Hirasawa.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1974413721","https://openalex.org/W1987906574","https://openalex.org/W2007748196","https://openalex.org/W2038237443","https://openalex.org/W2101609516","https://openalex.org/W2105454037","https://openalex.org/W2111966261","https://openalex.org/W2118692040","https://openalex.org/W2123649031","https://openalex.org/W2146083413","https://openalex.org/W2148154194","https://openalex.org/W2153909896","https://openalex.org/W2155572345","https://openalex.org/W2166159048","https://openalex.org/W2320053039"],"related_works":["https://openalex.org/W2289848901","https://openalex.org/W2001172292","https://openalex.org/W2169567031","https://openalex.org/W1849802015","https://openalex.org/W2354873283","https://openalex.org/W2023041720","https://openalex.org/W3097766872","https://openalex.org/W2353977479","https://openalex.org/W254031173","https://openalex.org/W1539630658"],"abstract_inverted_index":{"In":[0],"real-world":[1],"situations,":[2],"a":[3,21,26,34,44,49,58,74,89,102,130],"robot":[4],"may":[5],"often":[6],"encounter":[7],"\u201cunder-determined\u201d":[8],"situation,":[9],"where":[10],"there":[11],"are":[12,53],"more":[13],"sound":[14,79],"sources":[15],"than":[16],"microphones.":[17],"This":[18,99],"paper":[19,100],"presents":[20,101],"speech":[22,45,167],"separation":[23,46],"method":[24,47,104,164],"using":[25,147],"new":[27,131],"constraint":[28,132],"on":[29],"the":[30,92,107,118,122,126],"harmonic":[31,119,127],"structure":[32,128],"for":[33,43],"simultaneous":[35,50,145],"speech-recognition":[36,51],"system":[37,52],"in":[38,48,68,78,154],"under-determined":[39],"conditions.":[40],"The":[41,109,158],"requirements":[42],"(1)":[54],"ability":[55],"to":[56,105,133],"handle":[57],"large":[59],"number":[60],"of":[61,66],"talkers,":[62],"and":[63,116,121],"(2)":[64],"reduction":[65],"distortion":[67],"acoustic":[69],"features.":[70],"Conventional":[71],"methods":[72],"use":[73],"maximum":[75,113],"likelihood":[76,114],"estimation":[77,115],"source":[80],"separation,":[81],"which":[82],"fulfills":[83],"requirement":[84,135],"(1).":[85],"Since":[86],"it":[87],"is":[88,94],"general":[90],"approach,":[91],"performance":[93],"limited":[95],"when":[96],"separating":[97],"speech.":[98],"two-stage":[103],"improve":[106,166],"separation.":[108],"first":[110],"stage":[111,124],"uses":[112],"extracts":[117],"structure,":[120],"second":[123],"exploits":[125],"as":[129],"achieve":[134],"(2).":[136],"We":[137],"carried":[138],"out":[139],"an":[140,155],"experiment":[141],"that":[142,162],"simulated":[143],"three":[144],"utterances":[146],"impulse":[148],"responses":[149],"recorded":[150],"by":[151,170],"two":[152],"microphones":[153],"anechoic":[156],"chamber.":[157],"experimental":[159],"results":[160],"revealed":[161],"our":[163],"could":[165],"recognition":[168],"correctness":[169],"about":[171],"four":[172],"points.":[173]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}