Related papers: Speaker verification using end-to-end adversarial …

End-to-end automatic speech recognition (ASR) can achieve promising performance with large-scale training data. However, it is known that domain mismatch between training and testing data often leads to a degradation of recognition…

Recent advances in neural network based acoustic modelling have shown significant improvements in automatic speech recognition (ASR) performance. In order for acoustic models to be able to handle large acoustic variability, large amounts of…

This study addresses the problem of unsupervised subword unit discovery from untranscribed speech. It forms the basis of the ultimate goal of ZeroSpeech 2019, building text-to-speech systems without text labels. In this work, unit discovery…

Recent works on domain adaptation reveal the effectiveness of adversarial learning on filling the discrepancy between source and target domains. However, two common limitations exist in current adversarial-learning-based methods. First,…

In real-world applications, speaker recognition models often face various domain-mismatch challenges, leading to a significant drop in performance. Although numerous domain adaptation techniques have been developed to address this issue,…

Training models that are robust to data domain shift has gained an increasing interest both in academia and industry. Question-Answering language models, being one of the typical problem in Natural Language Processing (NLP) research, has…

The conventional speaker recognition frameworks (e.g., the i-vector and CNN-based approach) have been successfully applied to various tasks when the channel of the enrolment dataset is similar to that of the test dataset. However, in…

Transformer models have been used in automatic speech recognition (ASR) successfully and yields state-of-the-art results. However, its performance is still affected by speaker mismatch between training and test data. Further finetuning a…

Deep speaker embedding has achieved satisfactory performance in speaker verification. By enforcing the neural model to discriminate the speakers in the training set, deep speaker embedding (called `x-vectors`) can be derived from the hidden…

In real-life conditions, mismatch between development and test domain degrades speaker recognition performance. To solve the issue, many researchers explored domain adaptation approaches using matched in-domain dataset. However, adaptation…

We present a Lipreading system, i.e. a speech recognition system using only visual features, which uses domain-adversarial training for speaker independence. Domain-adversarial training is integrated into the optimization of a lipreader…

A great challenge in speaker representation learning using deep models is to design learning objectives that can enhance the discrimination of unseen speakers under unseen domains. This work proposes a supervised contrastive learning…

Unsupervised domain adaptation, which involves transferring knowledge from a label-rich source domain to an unlabeled target domain, can be used to substantially reduce annotation costs in the field of object detection. In this study, we…

Speaker verification, as a biometric authentication mechanism, has been widely used due to the pervasiveness of voice control on smart devices. However, the task of "in-the-wild" speaker verification is still challenging, considering the…

Domain gap often degrades the performance of speaker verification (SV) systems when the statistical distributions of training data and real-world test speech are mismatched. Channel variation, a primary factor causing this gap, is less…

Recent studies have highlighted adversarial examples as a ubiquitous threat to different neural network models and many downstream applications. Nonetheless, as unique data properties have inspired distinct and powerful learning principles,…

Despite the rapid progress of automatic speech recognition (ASR) technologies targeting normal speech in recent decades, accurate recognition of dysarthric and elderly speech remains highly challenging tasks to date. Sources of…

Deep neural network based speaker recognition systems can easily be deceived by an adversary using minuscule imperceptible perturbations to the input speech samples. These adversarial attacks pose serious security threats to the speaker…

Data augmentation (DA) has gained widespread popularity in deep speaker models due to its ease of implementation and significant effectiveness. It enriches training data by simulating real-life acoustic variations, enabling deep neural…

Adversarial attack approaches to speaker identification either need high computational cost or are not very effective, to our knowledge. To address this issue, in this paper, we propose a novel generation-network-based approach, called…