natural-language-processing-3

Zero-Shot Multi-Speaker TTS

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in zero-shot-multi-speaker-tts-9

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find zero-shot-multi-speaker-tts-9 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone

M. Ponti, Edresson Casanova, C. Shulby, Julian Weber, Arnaldo Cândido Júnior, Eren Gölge•Fri Dec 03 2021

The YourTTS model builds upon the VITS model and adds several novel modifications for zero-shot multi-speaker and multilingual training, achieving state-of-the-art (SOTA) results in zero- shot multi- Speaker TTS and results comparable to SOTA in zero -shot voice conversion on the VCTK dataset.

557

Content

0

Paper Graph

Stochastic Pitch Prediction Improves the Diversity and Naturalness of Speech in Glow-TTS

E. Vincent, Sewade Ogun, Vincent Colotte•Sat May 27 2023

This paper proposes to improve the diversity of utterances by explicitly learning the distribution of fundamental frequency sequences (pitch contours) of each speaker during training using a stochastic flow-based pitch predictor, then conditioning the model on generated pitch contours during inference.

5 0

Paper Graph

Adding a benchmark result helps the community track progress.