Ensemble prosody prediction for expressive speech synthesis

no code implementations • 3 Apr 2023 • Tian Huey Teh, Vivian Hu, Devang S Ram Mohan, Zack Hodari, Christopher G. R. Wallis, Tomás Gomez Ibarrondo, Alexandra Torresquintero, James Leoni, Mark Gales, Simon King

Generating expressive speech with rich and varied prosody continues to be a challenge for Text-to-Speech.

Ensemble Learning Expressive Speech Synthesis +1

Ctrl-P: Temporal Control of Prosodic Variation for Speech Synthesis

no code implementations • 15 Jun 2021 • Devang S Ram Mohan, Vivian Hu, Tian Huey Teh, Alexandra Torresquintero, Christopher G. R. Wallis, Marlene Staib, Lorenzo Foglianti, Jiameng Gao, Simon King

Text does not fully specify the spoken form, so text-to-speech models must be able to learn from speech data that vary in ways not explained by the corresponding text.

Speech Synthesis

ADEPT: A Dataset for Evaluating Prosody Transfer

no code implementations • 15 Jun 2021 • Alexandra Torresquintero, Tian Huey Teh, Christopher G. R. Wallis, Marlene Staib, Devang S Ram Mohan, Vivian Hu, Lorenzo Foglianti, Jiameng Gao, Simon King

Text-to-speech is now able to achieve near-human naturalness and research focus has shifted to increasing expressivity.

Incremental Text to Speech for Neural Sequence-to-Sequence Models using Reinforcement Learning

no code implementations • 7 Aug 2020 • Devang S Ram Mohan, Raphael Lenain, Lorenzo Foglianti, Tian Huey Teh, Marlene Staib, Alexandra Torresquintero, Jiameng Gao

We propose a reinforcement learning based framework to train an agent to make this decision.

Audio Generation reinforcement-learning +1

Phonological Features for 0-shot Multilingual Speech Synthesis

1 code implementation • 6 Aug 2020 • Marlene Staib, Tian Huey Teh, Alexandra Torresquintero, Devang S Ram Mohan, Lorenzo Foglianti, Raphael Lenain, Jiameng Gao

Code-switching---the intra-utterance use of multiple languages---is prevalent across the world.

Speech Synthesis