Abstract: We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data. We induce a pseudo language as a compact discrete representation, ...

Abstract: This paper features a power-efficient Viterbi decoder targeted for energy-efficient digital communication systems such as mobile and edge applications. An attempt has been made at a ...

Hearing a bird sing, a dog bark, an orca squeal has led so many of us to wonder if might be possible to talk to animals. Aza Raskin wants to listen to them. He's the co-founder and CEO of the Earth ...