2022/03/21 by Bac T. Nguyen, Nguyen, Bac, Fabien Cardinaux +3
Computer Science · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Natural Language Processing Techniques #Sound (cs.SD) #Speech Recognition and Synthesis #Topic Modeling #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2203.11049
openalex publication_date 2022/03/21 · openalex created_date 2022/04/03 · openalex updated_date 2026/07/28
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.