Regotron: Regularizing the Tacotron2 architecture via monotonic alignment loss

[PDF] arxiv.org

Utilizing Neural Transducers for Two-Stage Text-to-Speech via Semantic Token Prediction

M Kim, M Jeong, BJ Choi, S Kim, JY Lee… - arXiv preprint arXiv …, 2024 - arxiv.org
We propose a novel text-to-speech (TTS) framework centered around a neural transducer.
Our approach divides the whole TTS pipeline into semantic-level sequence-to-sequence …
被引用次数：1 相关文章 所有 2 个版本
[PDF] arxiv.org

Small-E: Small Language Model with Linear Attention for Efficient Speech Synthesis

T Lemerle, N Obin, A Roebel - arXiv preprint arXiv:2406.04467, 2024 - arxiv.org
Recent advancements in text-to-speech (TTS) powered by language models have
showcased remarkable capabilities in achieving naturalness and zero-shot voice cloning …
相关文章 所有 8 个版本