Author

Zexin Cai

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

Brain2Speech-Net: Fast and Intelligible Brain-to-Speech Synthesis Without Text Decoding

The loss of speech limits communication for individuals with paralysis. Direct neural-to-speech synthesis is challenging due to the limited availability of neural data for training speech brain-computer interfaces. Most existing systems rely on cascaded neural-to-text-to-speech pipelines, which increase inference laten...

Shreeram Suresh Chandra, Ze-Xin Cai, Yu Tsao et al. · 0 citations

Preprint Sep 2026

Brain2Speech-Net: Intelligible, Real-Time Brain-to-Speech Synthesis Without Text Decoding

Brain2Speech-Net is presented, among the first single-stage frameworks to remain intelligible under limited data while removing intermediate text decoding, and achieves strong intelligibility in objective and listening tests while running faster than real time.

Shreeram Suresh Chandra, Ze-Xin Cai, Yu Tsao et al. · 0 citations

#machine learning Apr 2026

DiffAnon: Diffusion-based Prosody Control for Voice Anonymization

DiffAnon is proposed, a diffusion-based anonymization method with classifier-free guidance (CFG) that provides explicit, continuous inference-time control over prosody preservation, and is the first voice anonymization framework to provide structured, interpolatable inference-time prosody control.

Ismail Rasim Ulgen, Zexin Cai, Nicholas Andrews et al. · arXiv.org · 0 citations