Related papers: Noise Adaptive Speech Enhancement using Domain Adv…

Self-Supervised Learning (SSL) has allowed leveraging large amounts of unlabeled speech data to improve the performance of speech recognition models even with small annotated datasets. Despite this, speech SSL representations may fail while…

It has been shown that the intelligibility of noisy speech can be improved by speech enhancement (SE) algorithms. However, monaural SE has not been established as an effective frontend for automatic speech recognition (ASR) in noisy…

In this paper, we initiate the concern of enhancing the spoofing robustness of the automatic speaker verification (ASV) system, without the primary presence of a separate countermeasure module. We start from the standard ASV framework of…

Diffusion models have achieved outstanding image generation by reversing a forward noising process to approximate true data distributions. During training, these models predict diffusion scores from noised versions of true samples in a…

Domain mismatch is a noteworthy issue in acoustic event detection tasks, as the target domain data is difficult to access in most real applications. In this study, we propose a novel CNN-based discriminative training framework as a domain…

Cross-lingual speech emotion recognition (SER) is a crucial task for many real-world applications. The performance of SER systems is often degraded by the differences in the distributions of training and test data. These differences become…

Large performance degradation is often observed for speaker ver-ification systems when applied to a new domain dataset. Givenan unlabeled target-domain dataset, unsupervised domain adaptation(UDA) methods, which usually leverage adversarial…

Existing adversarial domain adaptation methods mainly consider the marginal distribution and these methods may lead to either under transfer or negative transfer. To address this problem, we present a self-adaptive re-weighted adversarial…

The design of better automated dialogue evaluation metrics offers the potential of accelerate evaluation research on conversational AI. However, existing trainable dialogue evaluation models are generally restricted to classifiers trained…

Speech emotion recognition systems (SER) can achieve high accuracy when the training and test data are identically distributed, but this assumption is frequently violated in practice and the performance of SER systems plummet against…

A challenging problem in deep learning-based machine listening field is the degradation of the performance when using data from unseen conditions. In this paper we focus on the acoustic scene classification (ASC) task and propose an…

Automatic Speaker Verification (ASV) technology has become commonplace in virtual assistants. However, its performance suffers when there is a mismatch between the train and test domains. Mixed bandwidth training, i.e., pooling training…

Adversarial training (AT) is proved to reliably improve network's robustness against adversarial data. However, current AT with a pre-specified perturbation budget has limitations in learning a robust network. Firstly, applying a…

Speech systems developed for a particular choice of acoustic domain and sampling frequency do not translate easily to others. The usual practice is to learn domain adaptation and bandwidth extension models independently. Contrary to this,…

Compensation for channel mismatch and noise interference is essential for robust automatic speech recognition. Enhanced speech has been introduced into the multi-condition training of acoustic models to improve their generalization ability.…

Speech enhancement (SE) is proved effective in reducing noise from noisy speech signals for downstream automatic speech recognition (ASR), where multi-task learning strategy is employed to jointly optimize these two tasks. However, the…

Adversarial training (AT) refers to integrating adversarial examples -- inputs altered with imperceptible perturbations that can significantly impact model predictions -- into the training process. Recent studies have demonstrated the…

The phenomenon of adversarial examples illustrates one of the most basic vulnerabilities of deep neural networks. Among the variety of techniques introduced to surmount this inherent weakness, adversarial training has emerged as the most…

The recent advances in deep transfer learning reveal that adversarial learning can be embedded into deep networks to learn more transferable features to reduce the distribution discrepancy between two domains. Existing adversarial domain…

The performance of Human Activity Recognition (HAR) models, particularly deep neural networks, is highly contingent upon the availability of the massive amount of annotated training data which should be sufficiently labeled. Though, data…