We introduce COLA, a self-supervised pre-training approach for learning a general-purpose
representation of audio. Our approach is based on contrastive learning: it learns a …

This work follows the multi-label classification based paradigm for non-intrusive load
monitoring (NILM). Power consumption signals used for NILM are inherently time varying …

语音承载着人类语言和说话人身份信息, 通过语音伪造技术可以精确模仿目标说话人的声音以
达到欺骗人或机器听觉的目的. 目前, 深度伪造(Deepfake) 正在对全球的政治经济及社会稳定带 …

Prosodic modeling is a core problem in speech synthesis. The key challenge is producing
desirable prosody from textual input containing only phonetic information. In this preliminary …

Voice interfaces are becoming wildly popular and driving demand for more advanced
speech synthesis and voice transformation systems. Current text-to-speech methods …

The increasing use of Internet-of-Things (IoT) devices for monitoring a wide spectrum of
applications, along with the challenges of “big data” streaming support they often require for …

We propose a noise shaping method to improve the sound quality of speech signals
generated by WaveNet, which is a convolutional neural network (CNN) that predicts a …

Neural text-to-speech synthesis (NTTS) models have shown significant progress in
generating high-quality speech, however they require a large quantity of training data. This …

We propose a new visual servoing method that controls a robot's motion in a latent space.
We aim to extract the best properties of two previously proposed servoing methods: we seek …

Performance isolation is an essential property that network virtualization must provide for
clouds. This study addresses the performance isolation of the control plane in virtualized …