A blind segmentation approach to acoustic event detection based on i-vector

Huang, Zhen; Cheng, Yiwei; Li, Kehuang; Hautamäki, Ville; Lee, Chin‐Hui

doi:10.21437/interspeech.2013-535

Cited by 15 publications

(10 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional methods for AED apply techniques from ASR directly. For instance, Mel Frequency Cepstral Coefficients (MFCC) were modeled with Gaussian Mixture Models (GMM) or Support Vector Machines (SVM) [12,13,14,15]. Yet, applying standard ASR approaches leads to inferior performance due to differences between speech and non-speech signals.…”

Section: Introductionmentioning

confidence: 99%

Deep Convolutional Neural Networks and Data Augmentation for Acoustic Event Recognition

et al. 2016

View full text Add to dashboard Cite

We propose a novel method for Acoustic Event Detection (AED). In contrast to speech, sounds coming from acoustic events may be produced by a wide variety of sources. Furthermore, distinguishing them often requires analyzing an extended time period due to the lack of a clear sub-word unit. In order to incorporate the long-time frequency structure for AED, we introduce a convolutional neural network (CNN) with a large input field. In contrast to previous works, this enables to train audio event detection end-to-end. Our architecture is inspired by the success of VGGNet [1] and uses small, 3×3 convolutions, but more depth than previous methods in AED. In order to prevent over-fitting and to take full advantage of the modeling capabilities of our network, we further propose a novel data augmentation method to introduce data variation. Experimental results show that our CNN significantly outperforms state of the art methods including Bag of Audio Words (BoAW) and classical CNNs, achieving a 16% absolute improvement.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep Convolutional Neural Networks and Data Augmentation for Acoustic Event Recognition

et al. 2016

View full text Add to dashboard Cite

show abstract

“…The following section describes the experiments conducted on the GISE-51 Mixtures dataset. Previously addressed using classical approaches such as those based on i-vectors [15], Melfrequency cepstrum coefficient (MFCC) features and Gaussian Mixture models [16], there has been a recent shift towards applying deep neural networks for sound event recognition, including CNNs [3,17,18,19,20], Recurrent Neural Networks (RNNs) [21,22], as well as CNN-RNN hybrid approaches [23]. Instead of proposing a custom architecture, we instead focus on benchmarking convolutional neural networks from the prominent ResNet [24], DenseNet [25] and EfficientNet [26] paradigms to serve as baselines for future research.…”

Section: Methodsmentioning

confidence: 99%

GISE-51: A scalable isolated sound events dataset

Yadav,

Foster

2021

Preprint

View full text Add to dashboard Cite

Most of the existing isolated sound event datasets comprise a small number of sound event classes, usually 10 to 15, restricted to a small domain, such as domestic and urban sound events. In this work, we introduce GISE-51, a dataset spanning 51 isolated sound events belonging to a broad domain of event types. We also release GISE-51-Mixtures, a dataset of 5-second soundscapes with hard-labelled event boundaries synthesized from GISE-51 isolated sound events. We conduct baseline sound event recognition (SER) experiments on the GISE-51-Mixtures dataset, benchmarking prominent convolutional neural networks, and models trained with the dataset demonstrate strong transfer learning performance on existing audio recognition benchmarks. Together, GISE-51 and GISE-51-Mixtures attempt to address some of the shortcomings of recent sound event datasets, providing an open, reproducible benchmark for future research along with the freedom to adapt the included isolated sound events for domain-specific applications.

show abstract

“…However, such methods do not capture the complexity of real-life audio recordings. For event detection, researchers have therefore modeled audio using the second-order statistical covariance matrix of the low-level MFCC features [19,10,7,23]. There are two ways to compute the second-order statistics.…”

Section: Related Workmentioning

confidence: 99%

DCAR: A Discriminative and Compact Audio Representation for Audio Processing

Jing

Liu

Choi

et al. 2017

IEEE Trans. Multimedia

View full text Add to dashboard Cite

This paper presents a novel two-phase method for audio representation, Discriminative and Compact Audio Representation (DCAR), and evaluates its performance at detecting events in consumer-produced videos. In the first phase of DCAR, each audio track is modeled using a Gaussian mixture model (GMM) that includes several components to capture the variability within that track. The second phase takes into account both global structure and local structure. In this phase, the components are rendered more discriminative and compact by formulating an optimization problem on Grassmannian manifolds, which we found represents the structure of audio effectively.Our experiments used the YLI-MED dataset (an open TRECVID-style video corpus based on YFCC100M), which includes ten events. The results show that the proposed DCAR representation consistently outperforms state-of-the-art audio representations. DCAR's advantage over i-vector, mv-vector, and GMM representations is significant for both easier and harder discrimination tasks. We discuss how these performance differences across easy and hard cases follow from how each type of model leverages (or doesn't leverage) the intrinsic structure of the data. Furthermore, DCAR shows a particularly notable accuracy advantage on events where humans have more difficulty classifying the videos, i.e., events with lower mean annotator confidence. 1 * Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University,

show abstract

A blind segmentation approach to acoustic event detection based on i-vector

Cited by 15 publications

References 27 publications

Deep Convolutional Neural Networks and Data Augmentation for Acoustic Event Recognition

Deep Convolutional Neural Networks and Data Augmentation for Acoustic Event Recognition

GISE-51: A scalable isolated sound events dataset

DCAR: A Discriminative and Compact Audio Representation for Audio Processing

Contact Info

Product

Resources

About