Related papers: Probing the Robustness Properties of Neural Speech…

How to efficiently utilize the temporal features is crucial, yet challenging, for video restoration. The temporal features usually contain various noisy and uncorrelated information, and they may interfere with the restoration of the…

The main motivation for Automatic Speech Recognition (ASR) is efficient interfaces to computers, and for the interfaces to be natural and truly useful, it should provide coverage for a large group of users. The purpose of these tasks is to…

Quantization has emerged as an essential technique for deploying deep neural networks (DNNs) on devices with limited resources. However, quantized models exhibit vulnerabilities when exposed to various noises in real-world applications.…

Noise and decoherence are two major obstacles to the implementation of large-scale quantum computing. Because of the no-cloning theorem, which says we cannot make an exact copy of an arbitrary quantum state, simple redundancy will not work…

Recurrent Neural networks (RNN) have shown promising potential for learning dynamics of sequential data. However, artificial neural networks are known to exhibit poor robustness in presence of input noise, where the sequential architecture…

Departing from traditional communication theory where decoding algorithms are assumed to perform without error, a system where noise perturbs both computational devices and communication channels is considered here. This paper studies…

Quantization has emerged as a mainstream method for compressing Large Language Models (LLMs), reducing memory requirements and accelerating inference without architectural modifications. While existing research primarily focuses on…

Recently, neural vocoders have been widely used in speech synthesis tasks, including text-to-speech and voice conversion. However, when encountering data distribution mismatch between training and inference, neural vocoders trained on real…

We present SoundStream, a novel neural audio codec that can efficiently compress speech, music and general audio at bitrates normally targeted by speech-tailored codecs. SoundStream relies on a model architecture composed by a fully…

We introduce a state-of-the-art real-time, high-fidelity, audio codec leveraging neural networks. It consists in a streaming encoder-decoder architecture with quantized latent space trained in an end-to-end fashion. We simplify and speed-up…

We present our experiments in training robust to noise an end-to-end automatic speech recognition (ASR) model using intensive data augmentation. We explore the efficacy of fine-tuning a pre-trained model to improve noise robustness, and we…

We propose noise-robust voice conversion (VC) which takes into account the recording quality and environment of noisy source speech. Conventional denoising training improves the noise robustness of a VC model by learning noisy-to-clean VC…

The success of deep learning has sparked significant interest in designing computer hardware optimized for the high computational demands of neural network inference. As further miniaturization of digital CMOS processors becomes…

Large language models have revolutionized natural language processing through self-supervised pretraining on massive datasets. Inspired by this success, researchers have explored adapting these methods to speech by discretizing continuous…

Noisy labels are inevitable in large real-world datasets. In this work, we explore an area understudied by previous works -- how the network's architecture impacts its robustness to noisy labels. We provide a formal framework connecting the…

The neural codec model reduces speech data transmission delay and serves as the foundational tokenizer for speech language models (speech LMs). Preserving emotional information in codecs is crucial for effective communication and context…

This paper introduces a novel neural network-based speech coding system that can process noisy speech effectively. The proposed source-aware neural audio coding (SANAC) system harmonizes a deep autoencoder-based source separation model and…

Cortical sensory neurons are known to be highly variable, in the sense that responses evoked by identical stimuli often change dramatically from trial to trial. The origin of this variability is uncertain, but it is usually interpreted as…

The existence of adversarial data examples has drawn significant attention in the deep-learning community; such data are seemingly minimally perturbed relative to the original data, but lead to very different outputs from a deep-learning…

Semantic parsing is a technique aimed at constructing a structured representation of the meaning of a natural-language question. Recent advancements in few-shot language models trained on code have demonstrated superior performance in…