Unsupervised Domain Adaptation for Acoustic Scene Classification Using Band-Wise Statistics Matching

Mezza, Alessandro Ilic; Habets, Emanuël A. P.; Müller, Meinard; Sarti, Augusto

doi:10.23919/eusipco47968.2020.9287533

Cited by 12 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A modified SegNet [12], fine-resolution CNN (FR-CNN) [13] and a multi-scale feature fusion CNN [14] are other types of modified CNNs that have been used for ASC. The generative adversarial neural networks (GAN) [15], CNN with cross-entropy (CE) as loss function [16], CNN including a semantic neighbors over time (SeNoT) module [17], optimized CNNs [18][19][20] and conditional autoencoders [22] are among the deep learning methods used for audio scene classification. All of the above research has a similar feature: the use of log-Mel spectrogram.…”

Section: Deep Learning Methodsmentioning

confidence: 99%

“…Mel based features, such as log-Mel spectrogram, Mel-frequency cepstrum, MFCC, log-Mel delta, and delta-delta, are among the most commonly used features in ASC. For example, the Log-Mel spectrogram has been used in [8,[10][11][12][13][14][15][16][17][18][19][20][21][22], with differences between parameters such as filter banks, STFT and windowing function.…”

Section: Feature Extraction and Preprocessingmentioning

confidence: 99%

See 1 more Smart Citation

Binaural Acoustic Scene Classification Using Wavelet Scattering, Parallel Ensemble Classifiers and Nonlinear Fusion

Hajihashemi

Gharahbagh

Cruz³

et al. 2022

Sensors

View full text Add to dashboard Cite

The analysis of ambient sounds can be very useful when developing sound base intelligent systems. Acoustic scene classification (ASC) is defined as identifying the area of a recorded sound or clip among some predefined scenes. ASC has huge potential to be used in urban sound event classification systems. This research presents a hybrid method that includes a novel mathematical fusion step which aims to tackle the challenges of ASC accuracy and adaptability of current state-of-the-art models. The proposed method uses a stereo signal, two ensemble classifiers (random subspace), and a novel mathematical fusion step. In the proposed method, a stable, invariant signal representation of the stereo signal is built using Wavelet Scattering Transform (WST). For each mono, i.e., left and right, channel, a different random subspace classifier is trained using WST. A novel mathematical formula for fusion step was developed, its parameters being found using a Genetic algorithm. The results on the DCASE 2017 dataset showed that the proposed method has higher classification accuracy (about 95%), pushing the boundaries of existing methods.

show abstract

Section: Deep Learning Methodsmentioning

confidence: 99%

Section: Feature Extraction and Preprocessingmentioning

confidence: 99%

Binaural Acoustic Scene Classification Using Wavelet Scattering, Parallel Ensemble Classifiers and Nonlinear Fusion

Hajihashemi

Gharahbagh

Cruz³

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Whereas current SAD state-of-the-art solutions rely on the use of deep learning techniques, these applications depend strongly on the amount of labelled data available. In some specific scenarios, obtaining labelled data can be significantly expensive or even impossible, which is why unsupervised domain adaptation techniques are an active research topic [21,22]. Domain adaptation techniques aim to transfer the knowledge obtained from a source domain and transfer it to a target domain.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Adaptation of Deep Speech Activity Detection Models to Unseen Domains

et al. 2022

View full text Add to dashboard Cite

Speech activity detection (SAD) aims to accurately classify audio fragments containing human speech. Current state-of-the-art systems for the SAD task are mainly based on deep learning solutions. These applications usually show a significant drop in performance when test data are different from training data due to the domain shift observed. Furthermore, machine learning algorithms require large amounts of labelled data, which may be hard to obtain in real applications. Considering both ideas, in this paper we evaluate three unsupervised domain adaptation techniques applied to the SAD task. A baseline system is trained on a combination of data from different domains and then adapted to a new unseen domain, namely, data from Apollo space missions coming from the Fearless steps challenge. Experimental results demonstrate that domain adaptation techniques seeking to minimise the statistical distribution shift provide the most promising results. In particular, Deep CORAL method reports a 13% relative improvement in the original evaluation metric when compared to the unadapted baseline model. Further experiments show that the cascaded application of Deep CORAL and pseudo-labelling techniques can improve even more the results, yielding a significant 24% relative improvement in the evaluation metric when compared to the baseline system.

show abstract

“…Many UDA methods [11,12,13] have been proposed in computer vision field, but only a few studies (such as [14,15,16,17,18]) have applied UDA techniques to ASC models. In [17], authors follow a unsupervised domain adaptation neural network [19], and introduces it to learn a common subspace for the ASC problem.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Multi-Target Domain Adaptation for Acoustic Scene Classification

Yang¹,

Wang²,

Zou³

2021

Interspeech 2021

View full text Add to dashboard Cite

It is well known that the mismatch between training (source) and test (target) data distribution will significantly decrease the performance of acoustic scene classification (ASC) systems. To address this issue, domain adaptation (DA) is one solution and many unsupervised DA methods have been proposed. These methods focus on a scenario of single source domain to single target domain. However, we will face such problem that test data comes from multiple target domains. This problem can be addressed by producing one model per target domain, but this solution is too costly. In this paper, we propose a novel unsupervised multi-target domain adaption (MTDA) method for ASC, which can adapt to multiple target domains simultaneously and make use of the underlying relation among multiple domains. Specifically, our approach combines traditional adversarial adaptation with two novel discriminator tasks that learns a common subspace shared by all domains. Furthermore, we propose to divide the target domain into the easy-to-adapt and hard-to-adapt domain, which enables the system to pay more attention to hard-to-adapt domain in training. The experimental results on the DCASE 2020 Task 1-A dataset and the DCASE 2019 Task 1-B dataset show that our proposed method significantly outperforms the previous unsupervised DA methods.

show abstract

Unsupervised Domain Adaptation for Acoustic Scene Classification Using Band-Wise Statistics Matching

Cited by 12 publications

References 10 publications

Binaural Acoustic Scene Classification Using Wavelet Scattering, Parallel Ensemble Classifiers and Nonlinear Fusion

Binaural Acoustic Scene Classification Using Wavelet Scattering, Parallel Ensemble Classifiers and Nonlinear Fusion

Unsupervised Adaptation of Deep Speech Activity Detection Models to Unseen Domains

Unsupervised Multi-Target Domain Adaptation for Acoustic Scene Classification

Contact Info

Product

Resources

About