{"id":"https://openalex.org/W2115326869","doi":"https://doi.org/10.1109/icassp.2011.5946410","title":"Bird species recognition combining acoustic and sequence modeling","display_name":"Bird species recognition combining acoustic and sequence modeling","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2115326869","doi":"https://doi.org/10.1109/icassp.2011.5946410","mag":"2115326869"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5946410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5025265147","display_name":"Martin Graciarena","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Graciarena","raw_affiliation_strings":["SRI International, Inc., Menlo Park, CA, USA","SRI-International, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"SRI-International, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044308987","display_name":"Michelle Delplanche","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michelle Delplanche","raw_affiliation_strings":["SRI International, Inc., Menlo Park, CA, USA","SRI-International, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"SRI-International, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107174154","display_name":"Elizabeth Shriberg","orcid":"https://orcid.org/0009-0004-3779-4956"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elizabeth Shriberg","raw_affiliation_strings":["SRI International, Inc., Menlo Park, CA, USA","SRI-International, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"SRI-International, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":["SRI International, Inc., Menlo Park, CA, USA","SRI-International, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"SRI-International, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.4462,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.96551724,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"341","last_page":"344"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9912999868392944,"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":0.9556999802589417,"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":0.6751551628112793},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6106271743774414},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5083886981010437},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5077946782112122},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5011448860168457},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49308034777641296},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.49280813336372375},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4755370616912842},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45929425954818726},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4580904245376587},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.42786848545074463},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4221656322479248},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32931673526763916},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.2278536856174469},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.15006056427955627}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6751551628112793},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6106271743774414},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5083886981010437},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5077946782112122},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5011448860168457},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49308034777641296},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.49280813336372375},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4755370616912842},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45929425954818726},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4580904245376587},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.42786848545074463},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4221656322479248},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32931673526763916},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2278536856174469},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.15006056427955627},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5946410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.232.5709","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.232.5709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.speech.sri.com/papers/icassp2011-birdspecies.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.6100000143051147}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338291","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1572146192","https://openalex.org/W2003212690","https://openalex.org/W2041823554","https://openalex.org/W2108606783","https://openalex.org/W2118039276","https://openalex.org/W2122979854","https://openalex.org/W2149241068","https://openalex.org/W2150521923","https://openalex.org/W2156822626"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W2121652828","https://openalex.org/W3033124456","https://openalex.org/W80839609","https://openalex.org/W2735380212","https://openalex.org/W2018887914","https://openalex.org/W2541627266","https://openalex.org/W2177128624"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,97],"this":[3],"work":[4],"was":[5,104],"to":[6,10,24,65,86],"explore":[7],"modeling":[8],"techniques":[9],"improve":[11],"bird":[12,39,99],"species":[13,40,100],"classification":[14],"from":[15,29,59,107],"audio":[16],"samples.":[17],"We":[18,55,76,92],"first":[19],"developed":[20,50],"an":[21,78],"unsupervised":[22],"approach":[23],"obtain":[25],"approximate":[26],"note":[27,34,61],"models":[28,35],"acoustic":[30,74],"features.":[31,75],"From":[32],"these":[33],"we":[36],"created":[37],"a":[38,45,66,105],"recognition":[41,53],"system":[42,63,90,108],"by":[43,81],"leveraging":[44],"phone":[46],"n-gram":[47,62],"statistical":[48],"model":[49,69],"for":[51],"speaker":[52],"applications.":[54],"found":[56,77],"competitive":[57],"performance":[58],"the":[60,72,87,98],"compared":[64],"Gaussian":[67],"mixture":[68],"baseline":[70],"using":[71],"same":[73],"important":[79],"gain":[80,106],"doing":[82],"score-level":[83],"combination":[84],"relative":[85],"best":[88],"individual":[89],"results.":[91],"verified":[93],"that":[94],"on":[95],"most":[96],"under":[101],"study":[102],"there":[103],"combination.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
