Search Results for author:
Found 4 papers, 0 papers with code
Investigating self-supervised features for expressive, multilingual voice conversion
Unsupervised approaches are typically trained to reconstruct the input signal, which is composed of the content and the speaker information.
Lightweight End-to-end Text-to-speech Synthesis for low resource on-device applications
Recent works have shown that modelling raw waveform directly from text in an end-to-end (E2E) fashion produces more natural-sounding speech than traditional neural text-to-speech (TTS) systems based on a cascade or two-stage approach.
Voice Filter: Few-shot text-to-speech speaker adaptation using voice conversion as a post-processing module
It uses voice conversion (VC) as a post-processing module appended to a pre-existing high-quality TTS system and marks a conceptual shift in the existing TTS paradigm, framing the few-shot TTS problem as a VC task.
Improving the expressiveness of neural vocoding with non-affine Normalizing Flows
In the waveform reconstruction task, the proposed model closes the naturalness and signal quality gap from the original PW to recordings by $10\%$, and from other state-of-the-art neural vocoding systems by more than $60\%$.
