{"id":"https://openalex.org/W1976610042","doi":"https://doi.org/10.1109/mmsp.2010.5662068","title":"An N-gram model for unstructured audio signals toward information retrieval","display_name":"An N-gram model for unstructured audio signals toward information retrieval","publication_year":2010,"publication_date":"2010-10-01","ids":{"openalex":"https://openalex.org/W1976610042","doi":"https://doi.org/10.1109/mmsp.2010.5662068","mag":"1976610042"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2010.5662068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2010.5662068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Workshop on Multimedia Signal Processing","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/A5100762841","display_name":"Samuel Kim","orcid":"https://orcid.org/0000-0001-5237-6358"},"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":"Samuel Kim","raw_affiliation_strings":["Signal Anlaysis and Interpretation Laboratory (SAIL), University of Southern California, Los Angeles, USA","Signal Anlaysis and Interpretation Lab, (SAIL), University of Southern California, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"Signal Anlaysis and Interpretation Laboratory (SAIL), University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Signal Anlaysis and Interpretation Lab, (SAIL), University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113697636","display_name":"Shiva Sundaram","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]},{"id":"https://openalex.org/I4210093367","display_name":"Deutsche Telekom (Germany)","ror":"https://ror.org/00m8prc86","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210093367"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Shiva Sundaram","raw_affiliation_strings":["Deutsche Telekom Laboratories, Quality and Usability Lab, Technical University Berlin, Berlin, Germany","Deutsche Telekom Laboratories, Quality & Usability Lab, TU Berlin, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Deutsche Telekom Laboratories, Quality and Usability Lab, Technical University Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4210093367"]},{"raw_affiliation_string":"Deutsche Telekom Laboratories, Quality & Usability Lab, TU Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4210093367","https://openalex.org/I4577782"]}]},{"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":["Signal Anlaysis and Interpretation Laboratory (SAIL), University of Southern California, Los Angeles, USA","Signal Anlaysis and Interpretation Lab, (SAIL), University of Southern California, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"Signal Anlaysis and Interpretation Laboratory (SAIL), University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Signal Anlaysis and Interpretation Lab, (SAIL), University of Southern California, Los Angeles, 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":["Signal Anlaysis and Interpretation Laboratory (SAIL), University of Southern California, Los Angeles, USA","Signal Anlaysis and Interpretation Lab, (SAIL), University of Southern California, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"Signal Anlaysis and Interpretation Laboratory (SAIL), University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Signal Anlaysis and Interpretation Lab, (SAIL), University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100762841"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":1.3533,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.79495809,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"3","issue":null,"first_page":"477","last_page":"480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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":0.9991000294685364,"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":0.9975000023841858,"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":0.8014092445373535},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.6994781494140625},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5546236038208008},{"id":"https://openalex.org/keywords/onomatopoeia","display_name":"Onomatopoeia","score":0.5028287768363953},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.43631500005722046},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.43521058559417725},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41125285625457764},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.2898090183734894},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1629350483417511},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06743136048316956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8014092445373535},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.6994781494140625},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5546236038208008},{"id":"https://openalex.org/C22432085","wikidata":"https://www.wikidata.org/wiki/Q170239","display_name":"Onomatopoeia","level":2,"score":0.5028287768363953},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.43631500005722046},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.43521058559417725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41125285625457764},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2898090183734894},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1629350483417511},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06743136048316956},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":2,"locations":[{"id":"doi:10.1109/mmsp.2010.5662068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2010.5662068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Workshop on Multimedia Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.665.9037","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.665.9037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://worshipersam.net/www/pages/pdf_papers/MMSP2010-ngram.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1560013842","https://openalex.org/W1634005169","https://openalex.org/W1880262756","https://openalex.org/W1984251878","https://openalex.org/W2005529972","https://openalex.org/W2010486494","https://openalex.org/W2096637354","https://openalex.org/W2137337354","https://openalex.org/W2144037622","https://openalex.org/W2146078527","https://openalex.org/W2159277110","https://openalex.org/W2161755617","https://openalex.org/W6633431331","https://openalex.org/W6636654802","https://openalex.org/W6639619044"],"related_works":["https://openalex.org/W2315379384","https://openalex.org/W3197205159","https://openalex.org/W2313695185","https://openalex.org/W4280511947","https://openalex.org/W2767010592","https://openalex.org/W2369458119","https://openalex.org/W2327292841","https://openalex.org/W2003449491","https://openalex.org/W2124470186","https://openalex.org/W1964925579"],"abstract_inverted_index":{"An":[0],"N-gram":[1,18,79],"modeling":[2],"approach":[3,19,80,88],"for":[4],"unstructured":[5],"audio":[6,13,38,61],"signals":[7],"is":[8],"introduced":[9],"with":[10],"applications":[11],"to":[12,21,69],"information":[14,25],"retrieval.":[15],"The":[16],"proposed":[17,78],"aims":[20],"capture":[22],"local":[23,92],"dynamic":[24,93],"in":[26],"acoustic":[27,31,43,55],"words":[28],"within":[29],"the":[30,77],"topic":[32,47],"model":[33],"framework":[34],"which":[35],"assumes":[36],"an":[37],"signal":[39],"consists":[40],"of":[41],"latent":[42],"topics":[44],"and":[45,72],"each":[46],"can":[48],"be":[49],"interpreted":[50],"as":[51],"a":[52,86],"distribution":[53],"over":[54],"words.":[56],"Experimental":[57],"results":[58],"on":[59],"classifying":[60],"clips":[62],"from":[63],"BBC":[64],"Sound":[65],"Effects":[66],"Library":[67],"according":[68],"both":[70],"semantic":[71],"onomatopoeic":[73],"labels":[74],"indicate":[75],"that":[76],"performs":[81],"better":[82],"than":[83],"using":[84],"only":[85],"bag-of-words":[87],"by":[89],"providing":[90],"complementary":[91],"information.":[94]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}