We propose a new two-pass E2E speech recognition model that improves ASR...
In voice-enabled applications, a predetermined hotword isusually used to...
Recent success of the Tacotron speech synthesis architecture and its var...
Recognizing written domain numeric utterances (e.g. I need 1.25.) can be...
Lingvo is a Tensorflow framework offering a complete solution for
collab...
In this paper, we present a novel system that separates the voice of a t...