WaveNetEQ
Packet loss containment module
Screenshots

![]() View Image | ![]() View Image | ![]() View Image |
---|---|---|
Hunter's comment
A generative model, based on Google DeepMind WaveRNN technology; the WaveNetEQ packet loss containment module trains using a large speech data corpus enabling realistically continuing short speech segments it to fully synthesize the missing speech raw waveforms.
Link
http://ai.googleblog.com/2020/04/improving-audio-quality-in-duo-with.html

This is posted on Steemhunt - A place where you can dig products and earn STEEM.
View on Steemhunt.com