Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data?

[PDF] arxiv.org

CTC-based Non-autoregressive Textless Speech-to-Speech Translation

Q Fang, Z Ma, Y Zhou, M Zhang, Y Feng - arXiv preprint arXiv:2406.07330, 2024 - arxiv.org
Direct speech-to-speech translation (S2ST) has achieved impressive translation quality, but
it often faces the challenge of slow decoding due to the considerable length of speech …
被引用次数：1 相关文章 所有 2 个版本