Y Liu, Z Xu, G Wang, K Chen, B Li, X Tan, J Li… - arXiv preprint arXiv …, 2021 - arxiv.org
This paper describes the Microsoft end-to-end neural text to speech (TTS) system: DelightfulTTS for Blizzard Challenge 2021. The goal of this challenge is to synthesize …
C Miao, L Shuang, Z Liu, C Minchuan… - International …, 2021 - proceedings.mlr.press
In this work, we address the Text-to-Speech (TTS) task by proposing a non-autoregressive architecture called EfficientTTS. Unlike the dominant non-autoregressive TTS models, which …
Non-autoregressive architecture for neural text-to-speech (TTS) allows for parallel implementation, thus reduces inference time over its autoregressive counterpart. However …
Y Ma, J He, M Wu, G Hu, H Fei - Proc. Interspeech, 2023 - isca-archive.org
In pursuit of high inference speed, many non-autoregressive neural text-to-speech (TTS) models have been proposed for parallel speech synthesis recently. A critical challenge of …
X Tan - Neural Text-to-Speech Synthesis, 2023 - Springer
In this chapter, we introduce how to address the robustness issues in TTS. We summarize some popular techniques to improve robustness, including enhancing attention, replacing …