Computer Sciences

WaveGlow: A flow-based generative network to synthesize speech

A team of researchers at NVIDIA has recently developed WaveGlow, a flow-based network that can generate high-quality speech from melspectrograms, which are acoustic time-frequency representations of sound. Their method, outlined ...

Telecom

Artificial intelligence for optimized mobile communication

While many European states are currently setting up the 5th generation of mobile communication, scientists are already working on its optimization. Although 5G is far superior to its predecessors, even the latest mobile communication ...

Engineering

Headset over headphone: Canceling unnecessary and unwanted noise

Reporting in the journal Scientific Reports, the team of Tong Xiao, Xiaojun Qiu and Benjamin Halkon highlight the positive impacts for health and wellbeing of their 'virtual Active Noise Control/Cancelation (ANC) headphone' ...

Electronics & Semiconductors

Flexible low-voltage high-frequency organic thin-film transistors

Electronic applications on unconventional substrates that require low-temperature processing methods have primarily driven the development of organic thin-film transistors (TFTs) in the past few decades. Such applications ...

page 1 from 2