{"id":"https://openalex.org/W1988566301","doi":"https://doi.org/10.1109/mlsp.2015.7324316","title":"Retrieving sounds by vocal imitation recognition","display_name":"Retrieving sounds by vocal imitation recognition","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W1988566301","doi":"https://doi.org/10.1109/mlsp.2015.7324316","mag":"1988566301"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp.2015.7324316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2015.7324316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5100444198","display_name":"Yichi Zhang","orcid":"https://orcid.org/0000-0003-0465-6341"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yichi Zhang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY","Department of Electrical and Computer Engineering University of Rochester, Rochester, NY 14627"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering University of Rochester, Rochester, NY 14627","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102749436","display_name":"Zhiyao Duan","orcid":"https://orcid.org/0000-0002-8334-9974"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiyao Duan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY","Department of Electrical and Computer Engineering University of Rochester, Rochester, NY 14627"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering University of Rochester, Rochester, NY 14627","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100444198"],"corresponding_institution_ids":["https://openalex.org/I5388228"],"apc_list":null,"apc_paid":null,"fwci":1.737,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.8491216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"72","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.995199978351593,"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/imitation","display_name":"Imitation","score":0.8516884446144104},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7720212936401367},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.7371677160263062},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7303171157836914},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.539914608001709},{"id":"https://openalex.org/keywords/loudness","display_name":"Loudness","score":0.4541080594062805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43789416551589966},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2666550278663635},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11006811261177063}],"concepts":[{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.8516884446144104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7720212936401367},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.7371677160263062},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7303171157836914},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.539914608001709},{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.4541080594062805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43789416551589966},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2666550278663635},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11006811261177063},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mlsp.2015.7324316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2015.7324316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.725.3350","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.725.3350","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ece.rochester.edu/%7Ezduan/resource/ZhangDuan_RetrievingSoundsByVocalImitationRecognition_MLSP15.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W20241248","https://openalex.org/W153525290","https://openalex.org/W604354567","https://openalex.org/W1532076566","https://openalex.org/W2052900576","https://openalex.org/W2055922985","https://openalex.org/W2090493743","https://openalex.org/W2130325614","https://openalex.org/W2133257461","https://openalex.org/W2137259247","https://openalex.org/W2137337354","https://openalex.org/W2145065314","https://openalex.org/W2153635508","https://openalex.org/W2167700723","https://openalex.org/W2302720326","https://openalex.org/W6606292757","https://openalex.org/W6618552045","https://openalex.org/W6631814781","https://openalex.org/W6679718588","https://openalex.org/W6681363987","https://openalex.org/W6697852202"],"related_works":["https://openalex.org/W1107690805","https://openalex.org/W2097318409","https://openalex.org/W2739662815","https://openalex.org/W3007457309","https://openalex.org/W2038216521","https://openalex.org/W2736574136","https://openalex.org/W2565286512","https://openalex.org/W2399955410","https://openalex.org/W2097377227","https://openalex.org/W3126677997"],"abstract_inverted_index":{"Vocal":[0],"imitation":[1,50,108],"is":[2,52,93],"widely":[3],"used":[4],"in":[5,41,48,85,143],"human":[6],"communication.":[7],"In":[8],"this":[9,29],"paper,":[10],"we":[11,70],"propose":[12],"an":[13,86,139],"approach":[14],"to":[15,53,75],"automatically":[16,76],"recognize":[17,118],"the":[18],"concept":[19,112,121],"of":[20,28,67,82,98,109,113],"a":[21,45,64,72,80,90,105,110,126],"vocal":[22,49,83,107],"imitation,":[23],"and":[24,122,146],"then":[25],"retrieve":[26],"sounds":[27],"concept.":[30],"Because":[31],"different":[32,43],"acoustic":[33],"aspects":[34],"(e.g.,":[35],"pitch,":[36],"loudness,":[37],"timbre)":[38],"are":[39],"emphasized":[40],"imitating":[42],"sounds,":[44],"key":[46],"challenge":[47],"recognition":[51],"extract":[54],"appropriate":[55],"features.":[56],"Hand-crafted":[57],"features":[58,78],"may":[59],"not":[60],"work":[61],"well":[62],"for":[63,95],"large":[65],"variety":[66],"imitations.":[68,103],"Instead,":[69],"use":[71],"stacked":[73],"auto-encoder":[74],"learn":[77],"from":[79],"set":[81],"imitations":[84],"unsupervised":[87],"way.":[88],"Then,":[89],"multi-class":[91],"SVM":[92],"trained":[94],"sound":[96,111],"concepts":[97],"interest":[99],"using":[100],"their":[101],"training":[102],"Given":[104],"new":[106],"interest,":[114],"our":[115,135],"system":[116,136,142],"can":[117],"its":[119],"underlying":[120],"return":[123],"it":[124],"with":[125],"high":[127],"rank":[128],"among":[129],"all":[130],"concepts.":[131],"Experiments":[132],"show":[133],"that":[134],"significantly":[137],"outperforms":[138],"MFCC-based":[140],"comparison":[141],"both":[144],"classification":[145],"retrieval.":[147]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}