Promode Preprint
Posted ProMode, a zero-shot speech prosody model that maps text and reference audio to latent pitch, duration, and energy via a Perceiver-IO architecture, accepted to INTERSPEECH 2025. [arXiv]
Posted ProMode, a zero-shot speech prosody model that maps text and reference audio to latent pitch, duration, and energy via a Perceiver-IO architecture, accepted to INTERSPEECH 2025. [arXiv]