Related papers: Diagnostic-Driven Layer-Wise Compensation for Post…

Multiphysics problems such as multicomponent diffusion, phase transformations in multiphase systems and alloy solidification involve numerical solution of a coupled system of nonlinear partial differential equations (PDEs). Numerical…

Reducing the latency and model size has always been a significant research problem for live Automatic Speech Recognition (ASR) application scenarios. Along this direction, model quantization has become an increasingly popular approach to…

Machine learning based network intrusion detection systems are vulnerable to adversarial attacks that degrade classification performance under both gradient-based and distribution shift threat models. Existing defenses typically apply…

Despite significant work on low-bit quantization-aware training (QAT), there is still an accuracy gap between such techniques and native training. To address this, we introduce CAGE (Curvature-Aware Gradient Estimation), a new QAT method…

In the past years, the application of neural networks as an alternative to classical numerical methods to solve Partial Differential Equations has emerged as a potential paradigm shift in this century-old mathematical field. However, in…

We propose defensive tensorization, an adversarial defence technique that leverages a latent high-order factorization of the network. The layers of a network are first expressed as factorized tensor layers. Tensor dropout is then applied in…

Audio-visual speech enhancement system is regarded to be one of promising solutions for isolating and enhancing speech of desired speaker. Conventional methods focus on predicting clean speech spectrum via a naive convolution neural network…

We propose a new two-pass E2E speech recognition model that improves ASR performance by training on a combination of paired data and unpaired text data. Previously, the joint acoustic and text decoder (JATD) has shown promising results…

In sequence-to-sequence Transformer ASR, autoregressive (AR) models achieve strong accuracy but suffer from slow decoding, while non-autoregressive (NAR) models enable parallel decoding at the cost of degraded performance. We propose a…

Efficient inference is critical for deploying deep learning models on edge AI devices. Low-bit quantization (e.g., 3- and 4-bit) with fixed-point arithmetic improves efficiency, while low-power memory technologies like analog nonvolatile…

The quantized neural networks (QNNs) can be useful for neural network acceleration and compression, but during the training process they pose a challenge: how to propagate the gradient of loss function through the graph flow with a…

In this paper, we propose a single multi-task learning framework to perform End-to-End (E2E) speech recognition (ASR) and accent recognition (AR) simultaneously. The proposed framework is not only more compact but can also yield comparable…

Federated adversarial training can effectively complement adversarial robustness into the privacy-preserving federated learning systems. However, the high demand for memory capacity and computing power makes large-scale federated…

Recent advancement in Automatic Speech Recognition (ASR) has produced large AI models, which become impractical for deployment in mobile devices. Model quantization is effective to produce compressed general-purpose models, however such…

The performance of acoustic models degrades notably in noisy environments. Speech enhancement (SE) can be used as a front-end strategy to aid automatic speech recognition (ASR) systems. However, existing training objectives of SE methods…

The accuracy of end-to-end (E2E) automatic speech recognition (ASR) models continues to improve as they are scaled to larger sizes, with some now reaching billions of parameters. Widespread deployment and adoption of these models, however,…

Wake word (WW) spotting is challenging in far-field due to the complexities and variations in acoustic conditions and the environmental interference in signal transmission. A suite of carefully designed and optimized audio front-end (AFE)…

Single-word Automatic Speech Recognition (ASR) is a challenging task due to the lack of linguistic context and sensitivity to noise, pronunciation variation, and channel artifacts, especially in low-resource, communication-critical domains…

Cascaded Automatic Speech Recognition -- Large Language Model (ASR-LLM) pipelines remain popular for industrial Spoken Dialogue Systems (SDS), primarily because their decoupled design ensures perceptual verifiability. However, cascaded…

Automatic speech recognition (ASR) provides diverse audio-to-text services for humans to communicate with machines. However, recent research reveals ASR systems are vulnerable to various malicious audio attacks. In particular, by removing…