Recent advances in neural text-to-speech (TTS) models bring thousands of...
In this paper, we present ZeroPrompt (Figure 1-(a)) and the correspondin...
Recently, the unified streaming and non-streaming two-pass (U2/U2++)
end...
In this paper, we present TrimTail, a simple but effective emission
regu...
The recently proposed Conformer architecture which combines convolution ...
Keyword spotting (KWS) enables speech-based user interaction and gradual...
Recently, we made available WeNet, a production-oriented end-to-end spee...