Small and fast: only 123M parameters. High-quality voice cloning: state-of-the-art performance in speaker similarity, intelligibility, and naturalness. Multi-lingual: support Chinese and English.

UniSS is a unified single-stage speech-to-speech translation (S2ST) framework that achieves high translation fidelity and speech quality, while preserving timbre, emotion, and duration consistency.

Abstract: Imagined speech-based brain-computer interface (BCI) facilitates brain signal-driven intuitive communication which holds great promise as an effective speech rehabilitation tool, enabling ...

Abstract: This paper proposes a novel collaborative dysarthric speech recognition system designed to convert dysarthric speech into non-dysarthric speech to enhance the robustness of automatic speech ...

Bad Bunny gave a powerful speech about the Latino community at the Grammy Awards. The reggaeton superstar used his first acceptance speech of the night to address U.S. Immigration and Customs ...

With the United States' 2026 midterms a little over nine months away, President Donald Trump's low approval ratings are a major source of anxiety for GOP strategists. And a series of Democratic ...

These recent WhatsApp messages of a Venezuelan family – who asked to remain anonymous for fear of reprisals – underscore the caution civilians are taking in their daily conversations, on social media ...