Autotts: End-to-End Text-to-Speech Synthesis Through Differentiable Duration Modeling

Bac Nguyen; Fabien Cardinaux; Stefan Uhlich

ICASSP 2023accepted0 citations

Autotts: End-to-End Text-to-Speech Synthesis Through Differentiable Duration Modeling

Bac Nguyen, Fabien Cardinaux, Stefan Uhlich

Abstract

Parallel text-to-speech (TTS) models have recently enabled fast and highly-natural speech synthesis. However, they typically require external alignment models, which are not necessarily optimized for the decoder as they are not jointly trained. In this paper, we propose a differentiable duration method for learning monotonic alignments between input and output sequences. Our method is based on a soft-duration mechanism that optimizes a stochastic process in expectation. Using this differentiable duration method, we introduce AutoTTS, a direct text-to-waveform speech synthesis model. AutoTTS enables high-fidelity speech synthesis through a combination of adversarial training and matching the total ground-truth duration. Experimental results show that our model obtains competitive results while enjoying a much simpler training pipeline. Audio samples are available online <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> .

BibTeX

@inproceedings{icassp2023_autottsendtoendt,
  title = {Autotts: End-to-End Text-to-Speech Synthesis Through Differentiable Duration Modeling},
  author = {Bac Nguyen and Fabien Cardinaux and Stefan Uhlich},
  booktitle = {ICASSP 2023},
  year = {2023}
}