相关论文: Towards Evaluating the Robustness of Automatic Spe…

Automatic speech recognition (ASR) is improving ever more at mimicking human speech processing. The functioning of ASR, however, remains to a large extent obfuscated by the complex structure of the deep neural networks (DNNs) they are based…

While deep face recognition models have demonstrated remarkable performance, they often struggle on the inputs from domains beyond their training data. Recent attempts aim to expand the training set by relying on computationally expensive…

The demand for fast and accurate incremental speech recognition increases as the applications of automatic speech recognition (ASR) proliferate. Incremental speech recognizers output chunks of partially recognized words while the user is…

Adversarial perturbations exploit vulnerabilities in automatic speech recognition (ASR) systems while preserving human perceived linguistic content. Neural audio codecs impose a discrete bottleneck that can suppress fine-grained signal…

Large Language Models (LLMs) increasingly employ alignment techniques to prevent harmful outputs. Despite these safeguards, attackers can circumvent them by crafting adversarial prompts. Predominant token-level optimization methods…

Neural Style Transfer (NST) has quickly evolved from single-style to infinite-style models, also known as Arbitrary Style Transfer (AST). Although appealing results have been widely reported in literature, our empirical studies on four…

Although deep learning-based end-to-end Automatic Speech Recognition (ASR) has shown remarkable performance in recent years, it suffers severe performance regression on test samples drawn from different data distributions. Test-time…

Individuals with cerebral palsy (CP) and amyotrophic lateral sclerosis (ALS) frequently face challenges with articulation, leading to dysarthria and resulting in atypical speech patterns. In healthcare settings, communication breakdowns…

Speech accents present a serious challenge to the performance of state-of-the-art end-to-end Automatic Speech Recognition (ASR) systems. Even with self-supervised learning and pre-training of ASR models, accent invariance is seldom…

Adversarial attacks can mislead deep neural networks (DNNs) by adding imperceptible perturbations to benign examples. The attack transferability enables adversarial examples to attack black-box DNNs with unknown architectures or parameters,…

Voice-based interaction has emerged as a natural and intuitive modality for controlling IoT devices. However, speech-driven edge devices face a fundamental trade-off between cloud-based solutions, which offer stronger language understanding…

Currently, style augmentation is capturing attention due to convolutional neural networks (CNN) being strongly biased toward recognizing textures rather than shapes. Most existing styling methods either perform a low-fidelity style transfer…

Whisper is a recent Automatic Speech Recognition (ASR) model displaying impressive robustness to both out-of-distribution inputs and random noise. In this work, we show that this robustness does not carry over to adversarial noise. We show…

Thanks to the rise of self-supervised learning, automatic speech recognition (ASR) systems now achieve near-human performance on a wide variety of datasets. However, they still lack generalization capability and are not robust to domain…

Speaker adaptation techniques provide a powerful solution to customise automatic speech recognition (ASR) systems for individual users. Practical application of unsupervised model-based speaker adaptation techniques to data intensive…

Automatic Speech Recognition (ASR) systems are known to exhibit difficulties when transcribing children's speech. This can mainly be attributed to the absence of large children's speech corpora to train robust ASR models and the resulting…

This paper describes methods for evaluating automatic speech recognition (ASR) systems in comparison with human perception results, using measures derived from linguistic distinctive features. Error patterns in terms of manner, place and…

Audio adversarial examples are audio files that have been manipulated to fool an automatic speech recognition (ASR) system, while still sounding benign to a human listener. Most methods to generate such samples are based on a two-step…

Recent publications on automatic-speech-recognition (ASR) have a strong focus on attention encoder-decoder (AED) architectures which tend to suffer from over-fitting in low resource scenarios. One solution to tackle this issue is to…

Self-supervised learning (SSL) methods have proven to be very successful in automatic speech recognition (ASR). These great improvements have been reported mostly based on highly curated datasets such as LibriSpeech for non-streaming…