2 citations
5 papers
Enhancing Data-Free Adversarial Distillation with Activation Regularization and Virtual Interpolation
Xiaoyang Qu, Jianzong Wang, Jing Xiao
Knowledge distillation refers to a technique of transferring the knowledge from a large learned model or an ensemble of learned models to a small model. This method relies on acces…
GraphPB: Graphical Representations of Prosody Boundary in Speech Synthesis
Aolan Sun, Jianzong Wang, Ning Cheng +4
This paper introduces a graphical representation approach of prosody boundary (GraphPB) in the task of Chinese speech synthesis, intending to parse the semantic and syntactic relat…
MelGlow: Efficient Waveform Generative Network Based on Location-Variable Convolution
Zhen Zeng, Jianzong Wang, Ning Cheng +1
Recent neural vocoders usually use a WaveNet-like network to capture the long-term dependencies of the waveform, but a large number of parameters are required to obtain good modeli…
Multi-QuartzNet: Multi-Resolution Convolution for Speech Recognition with Multi-Layer Feature Fusion
Jian Luo, Jianzong Wang, Ning Cheng +2
In this paper, we propose an end-to-end speech recognition network based on Nvidia's previous QuartzNet model. We try to promote the model performance, and design three components:…
End-to-end Silent Speech Recognition with Acoustic Sensing
Jian Luo, Jianzong Wang, Ning Cheng +2
Silent speech interfaces (SSI) has been an exciting area of recent interest. In this paper, we present a non-invasive silent speech interface that uses inaudible acoustic signals t…