10 accepted papers
Deep learning has non-convex loss landscape and its optimization dynamics is hard to analyze or control. Nevertheless, the dynamics can be empirically convex-like across various tasks, models, optimizers, hyperparameters, etc. In this work, we examine the applicability of convexity and Lipschitz con…
Bidirectional language models (LMs) consistently show stronger context understanding than unidirectional models, yet the theoretical reason remains unclear. We present a simple information bottleneck (IB) perspective: bidirectional representations preserve more mutual information (MI) about both the…
We propose the generalized Newton's method (GeN) --- a Hessian-informed approach that applies to any optimizer such as SGD and Adam, and covers the Newton-Raphson method as a sub-case. Our method automatically and dynamically selects the learning rate that accelerates the convergence, without the in…
Deep neural network-based speech enhancement methods have become widespread, with one of its fundamental aspects being the effective extraction and application of features in the time-frequency domain. This paper proposes a hybrid feature global attention network (HFGANet) designed to efficiently ex…
In real-world scenarios, accent variations often reduce Automatic Speech Recognition (ASR) accuracy. Addressing this typically involves a multi-task ASR and Accent Recognition (ASR-AR) framework, but there is limited research on optimizing task-specific feature extraction and enhancing ASR with AR i…
During communication, volume changes, noise, and reverberation can disturb speech signals, significantly affecting the quality and intelligibility of speech. In the context of the ICASSP 2023 Signal Processing Grand Challenge, the first Speech Signal Improvement Grand Challenge (SIG) is organized to…
In denoising and de-reverberation tasks, the dominant methods are complex spectral masking and complex spectral mapping. To combine advantages and improve speech enhancement performance, we propose a two-stage UNet (TSUNet) to estimate complex spectral masking and complex spectral mapping. We use a…
Large convolutional neural networks (CNN) can be difficult to train in the differentially private (DP) regime, since the optimization algorithms require a computationally expensive operation, known as the per-sample gradient clipping. We propose an efficient and scalable implementation of this clipp…
When equipped with efficient optimization algorithms, the over-parameterized neural networks have demonstrated high level of performance even though the loss function is non-convex and non-smooth. While many works have been focusing on understanding the loss dynamics by training neural networks with…
Recent years have witnessed strong empirical performance of over-parameterized neural networks on various tasks and many advances in the theory, e.g. the universal approximation and provable convergence to global minimum. In this paper, we incorporate over-parameterized neural networks into semi-par…