- Apr 16, 2017
- 1,875
Google is now testing a new audio codec that aims to substantially improve audio quality on poor network connections. In a blog post, the Google AI team details its new high-quality, very low-bitrate speech codec they’ve named “Lyra.” Like traditional parametric codecs, Lyra’s basic architecture involves extracting distinctive speech attributes (also known as “features”) in the form of log Mel spectrograms that are then compressed, transmitted over the network, and recreated on the other end using a generative model.
Lyra’s basic architecture.
On the website there are audio samples you can hear and to my ears the difference is huge.