{"id":"https://openalex.org/W2035330281","doi":"https://doi.org/10.1109/icassp.2014.6853570","title":"Classification of clean and noisy bilingual movie audio for speech-to-speech translation corpora design","display_name":"Classification of clean and noisy bilingual movie audio for speech-to-speech translation corpora design","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2035330281","doi":"https://doi.org/10.1109/icassp.2014.6853570","mag":"2035330281"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6853570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5072740718","display_name":"Andreas Tsiartas","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andreas Tsiartas","raw_affiliation_strings":["Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","Dept. of Electr. Eng. Univ. of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Dept. of Electr. Eng. Univ. of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046000500","display_name":"Prasanta Ghosh","orcid":"https://orcid.org/0000-0002-2925-1802"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prasanta Kumar Ghosh","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Science (IISe), Bangalore, India","Dept. of Electr. Eng., Indian Inst. of Sci. (IISc), Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Science (IISe), Bangalore, India","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Indian Inst. of Sci. (IISc), Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021678540","display_name":"Panayiotis Georgiou","orcid":"https://orcid.org/0000-0002-0790-7161"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Panayiotis Georgiou","raw_affiliation_strings":["Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","Dept. of Electr. Eng. Univ. of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Dept. of Electr. Eng. Univ. of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","Dept. of Electr. Eng. Univ. of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Dept. of Electr. Eng. Univ. of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072740718"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.10561343,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"5","issue":null,"first_page":"121","last_page":"125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9987999796867371,"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/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.8246796727180481},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7219069004058838},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.6281465888023376},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.616233766078949},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4738198518753052},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4678885042667389},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4515973925590515},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4251604676246643},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4215725064277649},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4200003445148468},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.16887155175209045}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8246796727180481},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7219069004058838},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.6281465888023376},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.616233766078949},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4738198518753052},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4678885042667389},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4515973925590515},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4251604676246643},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4215725064277649},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4200003445148468},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.16887155175209045},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6853570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W229329885","https://openalex.org/W1490760466","https://openalex.org/W1492221128","https://openalex.org/W1565144712","https://openalex.org/W1975343484","https://openalex.org/W1999542175","https://openalex.org/W2061290937","https://openalex.org/W2101105183","https://openalex.org/W2122111042","https://openalex.org/W2127716729","https://openalex.org/W2142964468","https://openalex.org/W2159872955","https://openalex.org/W2293211712","https://openalex.org/W2404915168","https://openalex.org/W4244494905","https://openalex.org/W6600880057","https://openalex.org/W6608974995","https://openalex.org/W6680904902","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2138940226","https://openalex.org/W2264442632","https://openalex.org/W2051758472","https://openalex.org/W1543088868","https://openalex.org/W1501330897","https://openalex.org/W2550171623","https://openalex.org/W2964829415","https://openalex.org/W2131711534","https://openalex.org/W642007152","https://openalex.org/W2341426843"],"abstract_inverted_index":{"Identifying":[0],"suitable":[1,59],"sources":[2],"of":[3,13,43],"bilingual":[4,54,76,124],"audio":[5,47,55],"and":[6,20,45,62,81,107,120],"text":[7],"data":[8,38,56],"is":[9],"a":[10,29],"crucial":[11],"part":[12],"statistical":[14],"Speech":[15,17],"to":[16,115],"(S2S)":[18],"research":[19],"development.":[21],"Movies,":[22],"often":[23],"dubbed":[24],"in":[25,103,117,123],"other":[26,46],"languages,":[27],"offer":[28],"good":[30],"source":[31],"for":[32,60,66],"this":[33,72,105],"purpose;":[34],"but":[35],"not":[36],"all":[37],"are":[39,58],"directly":[40],"usable":[41],"because":[42],"noise":[44,93,97],"condition":[48],"differences.":[49],"Hence,":[50],"automatically":[51],"selecting":[52],"the":[53],"that":[57],"analysis,":[61],"training":[63],"S2S":[64],"systems":[65],"specific":[67],"environments":[68],"becomes":[69],"crucial.":[70],"In":[71],"work,":[73],"we":[74],"extract":[75],"speech":[77,88,90,122],"segments":[78,85],"from":[79],"movies":[80],"aim":[82],"at":[83],"classifying":[84],"as":[86],"clean":[87,119],"or":[89],"with":[91],"background":[92],"(i.e.":[94],"music,":[95],"babble":[96],"etc.).":[98],"We":[99],"examine":[100],"various":[101],"features":[102],"solving":[104],"problem":[106],"our":[108],"best":[109],"performing":[110],"method":[111],"delivers":[112],"accuracy":[113],"up":[114],"87%":[116],"discriminating":[118],"noisy":[121],"data.":[125]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}