Enhanced Feature Extraction Approaches for Detection of Sound Events

Surampudi, Naren; Srirangan, M; Christopher, Jabez

doi:10.1109/iacc48062.2019.8971574

Cited by 10 publications

(23 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When using SVM in combination with beamforming techniques, for example, the accuracy was greater than 80 % in all scenarios. In general, the nonparametric classifiers, SVM and KNN, were the ones that managed to reach the highest accuracy values, corroborating the results obtained in [10]. As mentioned, the computational cost of each algorithm was also a concern.…”

Section: Sgdsupporting

confidence: 84%

“…Therefore, the solutions used here address classic machine learning algorithms, seeking to find a balance between accuracy and computational cost. In [10], the authors also worked with audio classification for security systems and used two of the seven algorithms that will be covered in this article, K Nearest Neighbors (KNN) and Support Vector Machines (SVM). Similar to the previous one, [3] revealed that Random Forests can achieve high accuracy with MIVIA Dataset [11], specifically for surveillance applications, even with low SNR.…”

Section: Literature Reviewmentioning

confidence: 99%

“…After extraction, features were normalized. The work [10] explains the importance of this stage for the performance of the classifiers.…”

Section: A Datasetmentioning

confidence: 99%

See 2 more Smart Citations

Microphone Array Based Surveillance Audio Classification

Silva¹,

Spadini²,

Suyama³

2020

Anais De XXXVIII Simpósio Brasileiro De Telecomunicações E Processamento De Sinais

View full text Add to dashboard Cite

The work assessed seven classifiers and two beamforming algorithms for detecting surveillance sound events. The tests included the use of AWGN with -10 dB to 30 dB SNR and Data Augmentation (DA). The results showed that the combination of Support Vector Machine (SVM) and Delay-and-Sum (DaS) scored the best accuracy (up to 86.0%), but had high computational cost (≈ 79 ms), mainly due to DaS and DA. The use of Stochastic Gradient Descent (SGD) also seems to be a good alternative since it has achieved good accuracy either (up to 85.3%), but with quicker processing time (≈ 25 ms).

show abstract

Section: Sgdsupporting

confidence: 84%

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Microphone Array Based Surveillance Audio Classification

Silva¹,

Spadini²,

Suyama³

2020

Anais De XXXVIII Simpósio Brasileiro De Telecomunicações E Processamento De Sinais

View full text Add to dashboard Cite

show abstract

“…Recently, it has been widely acknowledged that rare event detection is a prominent area of research [8] within the domain of event detection. This area of research primarily focuses on the environment, health, and various industrial applications dealing with digital signals.…”

Section: Introductionmentioning

confidence: 99%

“…However, it is worth noting that the majority of research works concentrate on the realm of anomaly and outlier detection [8]. According to [9], the identification of different types of anomalous events can be challenging due to diverse patterns and typical incidents within distinct scenes.…”

Section: Introductionmentioning

confidence: 99%

A Systematic Review of Rare Events Detection Across Modalities using Machine Learning and Deep Learning

Abubakar,

OTHMANI,

Sabri

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>Rare event detection (RED) involves the identification and detection of events characterized by low frequency of occurrences, but of high importance or impact. This paper presents a Systematic Review (SR) of rare event detection across various modalities using Machine Learning (ML) and Deep Learning (DL) techniques. This review comprehensively outlines techniques and methods best suited for rare event detection across various modalities, while also highlighting future research prospects. To the extent of our knowledge, this paper is a pioneering SR dedicated to exploring this specific research domain. This SR identifies the employed methods and techniques, the datasets utilized, and the effectiveness of these methods in detecting rare events. Four modalities concerning RED are reviewed in this SR: video, sound, image, and time series. The corresponding performances for the different ML and DL techniques for RED are discussed comprehensively, together with the associated RED challenges and limitations as well as the directions for future research are highlighted. This SR aims to offer a comprehensive overview of the existing methods in RED, serving as a valuable resource for researchers and practitioners working in the respective field.</p>

show abstract

Parameter Tuning for Wavelet-Based Sound Event Detection Using Neural Networks

Raval

Christopher

2021

Artificial Intelligence in Music, Sound, Art and Design

View full text Add to dashboard Cite

Enhanced Feature Extraction Approaches for Detection of Sound Events

Cited by 10 publications

References 13 publications

Microphone Array Based Surveillance Audio Classification

Microphone Array Based Surveillance Audio Classification

A Systematic Review of Rare Events Detection Across Modalities using Machine Learning and Deep Learning

Parameter Tuning for Wavelet-Based Sound Event Detection Using Neural Networks

Contact Info

Product

Resources

About