10 citations · 25 across the 10 of their papers we have counts for
10 papers
Duplex Diffusion Models Improve Speech-to-Speech Translation
Xianchao Wu
Speech-to-speech translation is a typical sequence-to-sequence learning task that naturally has two directions. How to effectively leverage bidirectional supervision signals to pro…
Enhancing Unsupervised Speech Recognition with Diffusion GANs
Xianchao Wu
We enhance the vanilla adversarial training method for unsupervised Automatic Speech Recognition (ASR) by a diffusion-GAN. Our model (1) injects instance noises of various intensit…
Creative Painting with Latent Diffusion Models
Xianchao Wu
Artistic painting has achieved significant progress during recent years. Using an autoencoder to connect the original images with compressed latent spaces and a cross attention enh…
Attention Enhanced Citrinet for Speech Recognition
Xianchao Wu
Citrinet is an end-to-end convolutional Connectionist Temporal Classification (CTC) based automatic speech recognition (ASR) model. To capture local and global contextual informati…
Deep Sparse Conformer for Speech Recognition
Xianchao Wu
Conformer has achieved impressive results in Automatic Speech Recognition (ASR) by leveraging transformer's capturing of content-based global interactions and convolutional neural…
Improved Lower Bound for Analytic Schrödinger Eigenfunctions in Forbidden Regions
Xianchao Wu
The point of this paper is to improve the reverse Agmon estimate discussed in \cite{TW} with assuming that the Schrodinger operator , as $h…
Event-Driven Learning of Systematic Behaviours in Stock Markets
Xianchao Wu
It is reported that financial news, especially financial events expressed in news, provide information to investors' long/short decisions and influence the movements of stock marke…
Transformer-XL Based Music Generation with Multiple Sequences of Time-valued Notes
Xianchao Wu, Chengyuan Wang, Qinying Lei
Current state-of-the-art AI based classical music creation algorithms such as Music Transformer are trained by employing single sequence of notes with time-shifts. The major drawba…
Playing 20 Question Game with Policy-Based Reinforcement Learning
Huang Hu, Xianchao Wu, Bingfeng Luo +4
The 20 Questions (Q20) game is a well known game which encourages deductive reasoning and creativity. In the game, the answerer first thinks of an object such as a famous person or…
Reverse Agmon estimates and nodal intersection bounds in forbidden regions
John A. Toth, Xianchao Wu
Let be a compact, Riemannian manifold and . Given a regular energy level , we consider -normalized eigenfunctions, …