{"id":"https://openalex.org/W1992926722","doi":"https://doi.org/10.1109/roman.2007.4415064","title":"Speech/Music Discrimination for Robust Speech Recognition in Robots","display_name":"Speech/Music Discrimination for Robust Speech Recognition in Robots","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W1992926722","doi":"https://doi.org/10.1109/roman.2007.4415064","mag":"1992926722"},"language":"en","primary_location":{"id":"doi:10.1109/roman.2007.4415064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2007.4415064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"RO-MAN 2007 - The 16th IEEE International Symposium on Robot and Human Interactive Communication","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/A5041762657","display_name":"Mu Yeol Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I4921948","display_name":"Pusan National University","ror":"https://ror.org/01an57a31","country_code":"KR","type":"education","lineage":["https://openalex.org/I4921948"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mu Yeol Choi","raw_affiliation_strings":["Department of Electronics Engineering, Pusan National University, Busan, South Korea","Pusan National University, Pusan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics Engineering, Pusan National University, Busan, South Korea","institution_ids":["https://openalex.org/I4921948"]},{"raw_affiliation_string":"Pusan National University, Pusan#TAB#","institution_ids":["https://openalex.org/I4921948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034406505","display_name":"Hwa Jeon Song","orcid":"https://orcid.org/0000-0002-8216-4812"},"institutions":[{"id":"https://openalex.org/I4921948","display_name":"Pusan National University","ror":"https://ror.org/01an57a31","country_code":"KR","type":"education","lineage":["https://openalex.org/I4921948"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hwa Jeon Song","raw_affiliation_strings":["Research Institute of Computer Information and Communications, Pusan National University, Busan, South Korea","Research Institute of Computer Information and Communications, Pusan National University, Busan 609-735, Korea, e-mail: hwajeon@pusan.ac.kr"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Institute of Computer Information and Communications, Pusan National University, Busan, South Korea","institution_ids":["https://openalex.org/I4921948"]},{"raw_affiliation_string":"Research Institute of Computer Information and Communications, Pusan National University, Busan 609-735, Korea, e-mail: hwajeon@pusan.ac.kr","institution_ids":["https://openalex.org/I4921948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073733529","display_name":"Hyung Soon Kim","orcid":"https://orcid.org/0000-0001-5070-897X"},"institutions":[{"id":"https://openalex.org/I4921948","display_name":"Pusan National University","ror":"https://ror.org/01an57a31","country_code":"KR","type":"education","lineage":["https://openalex.org/I4921948"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyung Soon Kim","raw_affiliation_strings":["Department of Electronics Engineering, Pusan National University, Busan, South Korea","Member, IEEE, Department of Electronics Engineering, Pusan National University, Busan 609-735, Korea, e-mail: kimhs@pusan.ac.kr"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics Engineering, Pusan National University, Busan, South Korea","institution_ids":["https://openalex.org/I4921948"]},{"raw_affiliation_string":"Member, IEEE, Department of Electronics Engineering, Pusan National University, Busan 609-735, Korea, e-mail: kimhs@pusan.ac.kr","institution_ids":["https://openalex.org/I4921948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9765,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74638109,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"118","last_page":"121"},"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9995999932289124,"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/speech-recognition","display_name":"Speech recognition","score":0.8244677782058716},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.7954235672950745},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7485619783401489},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5954270362854004},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5812478065490723},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5641317963600159},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5023727416992188},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5014119148254395},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4584926664829254},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.417208194732666},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.40792155265808105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32789039611816406},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.06407082080841064}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8244677782058716},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.7954235672950745},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7485619783401489},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5954270362854004},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5812478065490723},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5641317963600159},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5023727416992188},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5014119148254395},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4584926664829254},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.417208194732666},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40792155265808105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32789039611816406},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.06407082080841064},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/roman.2007.4415064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2007.4415064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"RO-MAN 2007 - The 16th IEEE International Symposium on Robot and Human Interactive Communication","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2085457662","https://openalex.org/W2100820878","https://openalex.org/W2106055371","https://openalex.org/W2106339924","https://openalex.org/W2128838222","https://openalex.org/W3103998211"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W1614028504","https://openalex.org/W2888457666"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,36],"recognition":[2],"(ASR)":[3],"is":[4,37],"one":[5],"indispensable":[6],"technology":[7],"to":[8,29,87,92],"communicate":[9],"with":[10],"a":[11,75,112],"service":[12],"robot.":[13],"In":[14,33,70],"real-world":[15],"environments,":[16],"ASR":[17,31,34,83,98],"faces":[18],"many":[19],"kinds":[20],"of":[21,81,106],"sound":[22],"sources":[23],"and":[24,51],"they":[25,63],"should":[26],"be":[27,93],"discriminated":[28,58],"improve":[30],"performance.":[32],"systems,":[35],"usually":[38],"detected":[39],"from":[40],"the":[41,60,79,82,97,104,118,122],"input":[42,95],"signal":[43],"by":[44,59],"voice":[45],"activity":[46],"detection":[47],"(VAD)":[48],"scheme.":[49],"Speech":[50],"music,":[52],"how":[53],"ever,":[54],"are":[55],"not":[56,91],"easily":[57],"VAD":[61],"because":[62],"share":[64],"similar":[65],"characteristics":[66],"such":[67],"as":[68,111],"periodicity.":[69],"this":[71],"paper,":[72],"we":[73],"adopt":[74],"speech/music":[76,101],"discriminator":[77,102],"into":[78],"front-end":[80],"system":[84],"in":[85],"order":[86],"disable":[88],"music":[89],"stream":[90],"an":[94],"for":[96],"system.":[99],"Our":[100],"employs":[103],"mean":[105],"minimum":[107],"cepstral":[108],"distances":[109],"(MMCD)":[110],"feature":[113,124],"parameter.":[114],"Experimental":[115],"result":[116],"shows":[117],"MMCD":[119],"parameter":[120],"outperforms":[121],"conventional":[123],"parameter,":[125],"spectral":[126],"flux.":[127]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}