Large-scale self-supervised pre-trained speech encoders outperform
conve...
What does it take to create the Babel Fish, a tool that can help individ...
Speech-to-speech translation (S2ST) enables spoken communication between...
Transducer and Attention based Encoder-Decoder (AED) are two widely used...
We present SpeechMatrix, a large-scale multilingual corpus of
speech-to-...
We describe a method to jointly pre-train speech and text in an
encoder-...
For large-scale discrete-time algebraic Riccati equations (DAREs) with
h...
A quadratic dynamical system with practical applications is taken into
c...
Posterior collapse plagues VAEs for text, especially for conditional tex...