Related papers: SlothSpeech: Denial-of-service Attack Against Spee…
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…
In the past few years, it has been shown that deep learning systems are highly vulnerable under attacks with adversarial examples. Neural-network-based automatic speech recognition (ASR) systems are no exception. Targeted and untargeted…
Automatic speech recognition (ASR) systems are ubiquitously present in our daily devices. They are vulnerable to adversarial attacks, where manipulated input samples fool the ASR system's recognition. While adversarial examples for various…
The ubiquitous presence of machine learning systems in our lives necessitates research into their vulnerabilities and appropriate countermeasures. In particular, we investigate the effectiveness of adversarial attacks and defenses against…
Speech-enabled systems typically first convert audio to text through an automatic speech recognition (ASR) model and then feed the text to downstream natural language processing (NLP) modules. The errors of the ASR system can seriously…
Multi-speaker automatic speech recognition (ASR) aims to transcribe conversational speech involving multiple speakers, requiring the model to capture not only what was said, but also who said it and sometimes when it was spoken. Recent…
Automatic speech recognition systems have undoubtedly advanced with the integration of multilingual and multitask models such as Whisper, which have shown a promising ability to understand and process speech across a wide range of…
In recent years, significant progress has been made in deep model-based automatic speech recognition (ASR), leading to its widespread deployment in the real world. At the same time, adversarial attacks against deep ASR systems are highly…
While Automatic Speech Recognition has been shown to be vulnerable to adversarial attacks, defenses against these attacks are still lagging. Existing, naive defenses can be partially broken with an adaptive attack. In classification tasks,…
Large language model (LLM)-based automatic speech recognition (ASR) has recently attracted a lot of attention due to its high recognition accuracy and enhanced multi-dialect support. However, the high decoding latency of LLMs challenges the…
Self-supervised learning (SSL) of speech has shown impressive results in speech-related tasks, particularly in automatic speech recognition (ASR). While most methods employ the output of intermediate layers of the SSL model as real-valued…
Speech-based virtual assistants, such as Amazon Alexa, Google assistant, and Apple Siri, typically convert users' audio signals to text data through automatic speech recognition (ASR) and feed the text to downstream dialog models for…
In light of the widespread application of Automatic Speech Recognition (ASR) systems, their security concerns have received much more attention than ever before, primarily due to the susceptibility of Deep Neural Networks. Previous studies…
In automatic speech recognition (ASR), model pruning is a widely adopted technique that reduces model size and latency to deploy neural network models on edge devices with resource constraints. However, multiple models with different…
Scaling Text-to-speech (TTS) to large-scale datasets has been demonstrated as an effective method for improving the diversity and naturalness of synthesized speech. At the high level, previous large-scale TTS models can be categorized into…
Linguistic anomalies detectable in spontaneous speech have shown promise for various clinical applications including screening for dementia and other forms of cognitive impairment. The feasibility of deploying automated tools that can…
In interactive automatic speech recognition (ASR) systems, low-latency requirements limit the amount of search space that can be explored during decoding, particularly in end-to-end neural ASR. In this paper, we present a novel streaming…
The emergence of large-scale automatic speech recognition (ASR) models such as Whisper has greatly expanded their adoption across diverse real-world applications. Ensuring robustness against even minor input perturbations is therefore…
Speech enabled foundation models, either in the form of flexible speech recognition based systems or audio-prompted large language models (LLMs), are becoming increasingly popular. One of the interesting aspects of these models is their…
Whisper's robust performance in automatic speech recognition (ASR) is often attributed to its massive 680k-hour training set, an impractical scale for most researchers. In this work, we examine how linguistic and acoustic diversity in…