Related papers: MP3 Compression To Diminish Adversarial Noise in E…
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…
Acoustic echo cancellation (AEC) aims to remove interference signals while leaving near-end speech least distorted. As the indistinguishable patterns between near-end speech and interference signals, near-end speech can't be separated…
Deep neural network-based classifiers are prone to errors when processing adversarial examples (AEs). AEs are minimally perturbed input data undetectable to humans posing significant risks to security-dependent applications. Hence,…
Dense retrievers encode queries and documents and map them in an embedding space using pre-trained language models. These embeddings need to be high-dimensional to fit training signals and guarantee the retrieval effectiveness of dense…
Recent works have revealed the vulnerability of automatic speech recognition (ASR) models to adversarial examples (AEs), i.e., small perturbations that cause an error in the transcription of the audio signal. Studying audio adversarial…
The application of deep recurrent networks to audio transcription has led to impressive gains in automatic speech recognition (ASR) systems. Many have demonstrated that small adversarial perturbations can fool deep neural networks into…
Deep Reinforcement Learning (DRL) policies are highly susceptible to adversarial noise in observations, which poses significant risks in safety-critical scenarios. The challenge inherent to adversarial perturbations is that by altering the…
Environmental audio tagging aims to predict only the presence or absence of certain acoustic events in the interested acoustic scene. In this paper we make contributions to audio tagging in two parts, respectively, acoustic modeling and…
Detecting anomalies for multivariate time-series without manual supervision continues a challenging problem due to the increased scale of dimensions and complexity of today's IT monitoring systems. Recent progress of unsupervised…
Speaker adaptation systems face privacy concerns, for such systems are trained on private datasets and often overfitting. This paper demonstrates that an attacker can extract speaker information by querying speaker-adapted speech…
Autoencoder (AE) is the key to the success of latent diffusion models for image and video generation, reducing the denoising resolution and improving efficiency. However, the power of AE has long been underexplored in terms of network…
One challenging problem of robust automatic speech recognition (ASR) is how to measure the goodness of a speech enhancement algorithm (SEA) without calculating the word error rate (WER) due to the high costs of manual transcriptions,…
In this paper, we present a novel adversarial lossy video compression model. At extremely low bit-rates, standard video coding schemes suffer from unpleasant reconstruction artifacts such as blocking, ringing etc. Existing learned neural…
To achieve robust far-field automatic speech recognition (ASR), existing techniques typically employ an acoustic front end (AFE) cascaded with a neural transducer (NT) ASR model. The AFE output, however, could be unreliable, as the…
Variational auto-encoders (VAEs) are deep generative latent variable models that can be used for learning the distribution of complex data. VAEs have been successfully used to learn a probabilistic prior over speech signals, which is then…
Respiratory rate (RR) is a key vital sign for clinical assessment and mental well-being, yet it is rarely monitored in everyday life due to the lack of unobtrusive sensing technologies. In-ear audio sensing is promising due to its high…
In this paper, we proposed AI-based audio coding using MFCC features in an adversarial setting. We combined a conventional encoder with an adversarial learning decoder to better reconstruct the original waveform. Since GAN gives implicit…
Extremum-seeking control (ESC) is widely used to optimize performance when the system dynamics are uncertain. However, sensitivity to sensor noise is a crucial issue in ESC implementation due to the use of high-pass filters or gradient…
Despite recent improvements in End-to-End Automatic Speech Recognition (E2E ASR) systems, the performance can degrade due to vocal characteristic mismatches between training and testing data, particularly with limited target speaker…
Adversarial audio attacks can be considered as a small perturbation unperceptive to human ears that is intentionally added to the audio signal and causes a machine learning model to make mistakes. This poses a security concern about the…