Few-shot Bioacoustic Event Detection with Machine Learning Methods

Few-shot learning is a type of classification through which predictions are made based on a limited number of samples for each class. This type of classification is sometimes referred to as a meta-learning problem, in which the model learns how to learn to identify rare cases. We seek to extract inf...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chowenhill, Leah, Satyanath, Gaurav, Singh, Shubhranshu, Wagh, Madhav Mahendra
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Chowenhill, Leah
Satyanath, Gaurav
Singh, Shubhranshu
Wagh, Madhav Mahendra
description Few-shot learning is a type of classification through which predictions are made based on a limited number of samples for each class. This type of classification is sometimes referred to as a meta-learning problem, in which the model learns how to learn to identify rare cases. We seek to extract information from five exemplar vocalisations of mammals or birds and detect and classify these sounds in field recordings [2]. This task was provided in the Detection and Classification of Acoustic Scenes and Events (DCASE) Challenge of 2021. Rather than utilize deep learning, as is most commonly done, we formulated a novel solution using only machine learning methods. Various models were tested, and it was found that logistic regression outperformed both linear regression and template matching. However, all of these methods over-predicted the number of events in the field recordings.
doi_str_mv 10.48550/arxiv.2211.00569
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2211_00569</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2211_00569</sourcerecordid><originalsourceid>FETCH-LOGICAL-a679-2227cd8c992bf1b47c60c0b6f2c8cbda1182febd089b5e27bf8cbe59c0e034213</originalsourceid><addsrcrecordid>eNotz7FOwzAUhWEvDKjwAEz1CyTYN3Fij7S0gJSqS_fIvrkmlsBGiWnh7YHS6Uj_cKSPsTspylorJe7t9BWOJYCUpRCqMddstaVTMY8p81VIFtPnnAPyzZFi5o-UCXNIkZ9CHvnO4hgi8Y7sFEN85TvKYxrmG3bl7dtMt5ddsMN2c1g_F93-6WX90BW2aU0BAC0OGo0B56WrW2wECtd4QI1usFJq8OQGoY1TBK3zv5mUQUGiqkFWC7b8vz0j-o8pvNvpu__D9GdM9QO6Z0Tv</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Few-shot Bioacoustic Event Detection with Machine Learning Methods</title><source>arXiv.org</source><creator>Chowenhill, Leah ; Satyanath, Gaurav ; Singh, Shubhranshu ; Wagh, Madhav Mahendra</creator><creatorcontrib>Chowenhill, Leah ; Satyanath, Gaurav ; Singh, Shubhranshu ; Wagh, Madhav Mahendra</creatorcontrib><description>Few-shot learning is a type of classification through which predictions are made based on a limited number of samples for each class. This type of classification is sometimes referred to as a meta-learning problem, in which the model learns how to learn to identify rare cases. We seek to extract information from five exemplar vocalisations of mammals or birds and detect and classify these sounds in field recordings [2]. This task was provided in the Detection and Classification of Acoustic Scenes and Events (DCASE) Challenge of 2021. Rather than utilize deep learning, as is most commonly done, we formulated a novel solution using only machine learning methods. Various models were tested, and it was found that logistic regression outperformed both linear regression and template matching. However, all of these methods over-predicted the number of events in the field recordings.</description><identifier>DOI: 10.48550/arxiv.2211.00569</identifier><language>eng</language><subject>Computer Science - Sound</subject><creationdate>2022-08</creationdate><rights>http://creativecommons.org/licenses/by-nc-nd/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2211.00569$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2211.00569$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Chowenhill, Leah</creatorcontrib><creatorcontrib>Satyanath, Gaurav</creatorcontrib><creatorcontrib>Singh, Shubhranshu</creatorcontrib><creatorcontrib>Wagh, Madhav Mahendra</creatorcontrib><title>Few-shot Bioacoustic Event Detection with Machine Learning Methods</title><description>Few-shot learning is a type of classification through which predictions are made based on a limited number of samples for each class. This type of classification is sometimes referred to as a meta-learning problem, in which the model learns how to learn to identify rare cases. We seek to extract information from five exemplar vocalisations of mammals or birds and detect and classify these sounds in field recordings [2]. This task was provided in the Detection and Classification of Acoustic Scenes and Events (DCASE) Challenge of 2021. Rather than utilize deep learning, as is most commonly done, we formulated a novel solution using only machine learning methods. Various models were tested, and it was found that logistic regression outperformed both linear regression and template matching. However, all of these methods over-predicted the number of events in the field recordings.</description><subject>Computer Science - Sound</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz7FOwzAUhWEvDKjwAEz1CyTYN3Fij7S0gJSqS_fIvrkmlsBGiWnh7YHS6Uj_cKSPsTspylorJe7t9BWOJYCUpRCqMddstaVTMY8p81VIFtPnnAPyzZFi5o-UCXNIkZ9CHvnO4hgi8Y7sFEN85TvKYxrmG3bl7dtMt5ddsMN2c1g_F93-6WX90BW2aU0BAC0OGo0B56WrW2wECtd4QI1usFJq8OQGoY1TBK3zv5mUQUGiqkFWC7b8vz0j-o8pvNvpu__D9GdM9QO6Z0Tv</recordid><startdate>20220809</startdate><enddate>20220809</enddate><creator>Chowenhill, Leah</creator><creator>Satyanath, Gaurav</creator><creator>Singh, Shubhranshu</creator><creator>Wagh, Madhav Mahendra</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220809</creationdate><title>Few-shot Bioacoustic Event Detection with Machine Learning Methods</title><author>Chowenhill, Leah ; Satyanath, Gaurav ; Singh, Shubhranshu ; Wagh, Madhav Mahendra</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a679-2227cd8c992bf1b47c60c0b6f2c8cbda1182febd089b5e27bf8cbe59c0e034213</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Sound</topic><toplevel>online_resources</toplevel><creatorcontrib>Chowenhill, Leah</creatorcontrib><creatorcontrib>Satyanath, Gaurav</creatorcontrib><creatorcontrib>Singh, Shubhranshu</creatorcontrib><creatorcontrib>Wagh, Madhav Mahendra</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Chowenhill, Leah</au><au>Satyanath, Gaurav</au><au>Singh, Shubhranshu</au><au>Wagh, Madhav Mahendra</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Few-shot Bioacoustic Event Detection with Machine Learning Methods</atitle><date>2022-08-09</date><risdate>2022</risdate><abstract>Few-shot learning is a type of classification through which predictions are made based on a limited number of samples for each class. This type of classification is sometimes referred to as a meta-learning problem, in which the model learns how to learn to identify rare cases. We seek to extract information from five exemplar vocalisations of mammals or birds and detect and classify these sounds in field recordings [2]. This task was provided in the Detection and Classification of Acoustic Scenes and Events (DCASE) Challenge of 2021. Rather than utilize deep learning, as is most commonly done, we formulated a novel solution using only machine learning methods. Various models were tested, and it was found that logistic regression outperformed both linear regression and template matching. However, all of these methods over-predicted the number of events in the field recordings.</abstract><doi>10.48550/arxiv.2211.00569</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2211.00569
ispartof
issn
language eng
recordid cdi_arxiv_primary_2211_00569
source arXiv.org
subjects Computer Science - Sound
title Few-shot Bioacoustic Event Detection with Machine Learning Methods
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T16%3A35%3A30IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Few-shot%20Bioacoustic%20Event%20Detection%20with%20Machine%20Learning%20Methods&rft.au=Chowenhill,%20Leah&rft.date=2022-08-09&rft_id=info:doi/10.48550/arxiv.2211.00569&rft_dat=%3Carxiv_GOX%3E2211_00569%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true