{"id":"https://openalex.org/W155522212","doi":"https://doi.org/10.21437/interspeech.2007-740","title":"Audio classification using extended baum-welch transformations","display_name":"Audio classification using extended baum-welch transformations","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W155522212","doi":"https://doi.org/10.21437/interspeech.2007-740","mag":"155522212"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-740","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},"type":"conference-paper","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/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tara N. Sainath","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109575396","display_name":"Victor W. Zue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Victor Zue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5046671967","display_name":"Dimitri Kanevsky","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dimitri Kanevsky","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2067,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75094817,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2969","last_page":"2972"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9976999759674072,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9861999750137329,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/discriminative-model","display_name":"Discriminative model","score":0.8107743263244629},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7472891807556152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6860352754592896},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6383026242256165},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6293375492095947},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6111047863960266},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5952959060668945},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5207017064094543},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.484609454870224},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.46719953417778015},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4481302499771118},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.24271848797798157}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8107743263244629},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7472891807556152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6860352754592896},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6383026242256165},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6293375492095947},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6111047863960266},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5952959060668945},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5207017064094543},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.484609454870224},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.46719953417778015},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4481302499771118},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.24271848797798157},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2007-740","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.154.6832","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.154.6832","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sls.csail.mit.edu/sls/publications/2007/tsainath_icslp2007.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W206961783","https://openalex.org/W2033565080","https://openalex.org/W2074188409","https://openalex.org/W2128838222","https://openalex.org/W2149317649","https://openalex.org/W2153937809","https://openalex.org/W2168441989"],"related_works":["https://openalex.org/W2146591867","https://openalex.org/W2289868279","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W1975359510","https://openalex.org/W3004352674","https://openalex.org/W2769884427"],"abstract_inverted_index":{"Audio":[0],"classification":[1,66,86],"has":[2],"applications":[3],"in":[4,18,48],"a":[5,33],"variety":[6],"of":[7,39,59],"contexts,":[8],"such":[9],"as":[10,32],"automatic":[11],"sound":[12],"analysis,":[13],"supervised":[14],"audio":[15,19,50,65,90],"segmentation":[16],"and":[17,22,80],"information":[20],"search":[21],"retrieval.":[23],"Extended":[24],"Baum-Welch":[25],"(EBW)":[26],"transformations":[27,61],"are":[28],"most":[29],"commonly":[30],"used":[31],"discriminative":[34],"technique":[35],"for":[36],"estimating":[37],"parameters":[38],"Gaussian":[40,81],"mixtures,":[41],"though":[42],"recently":[43],"they":[44],"have":[45],"been":[46],"applied":[47],"unsupervised":[49],"segmentation.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55],"extend":[56],"the":[57,75],"use":[58],"these":[60],"to":[62],"derive":[63],"an":[64],"algorithm.":[67],"We":[68],"find":[69],"that":[70],"our":[71],"method":[72],"outperforms":[73],"both":[74],"Support":[76],"Vector":[77],"Machine":[78],"(SVM)":[79],"Mixture":[82],"Model":[83],"(GMM)":[84],"likelihood":[85],"methods.":[87],"Index":[88],"Terms:":[89],"classification,":[91],"gradient":[92],"methods":[93],"1.":[94]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}