conftrace_

speaker fidelity

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

phoneme-level modeling (1) vocoder synthesis (1) pre-trained audio encoder (1) speech naturalness (1) audio embedding (1) text-to-speech synthesis (1) latent diffusion model (1) classifier-free guidance (1) speech enhancement (1)

Papers

Efficient Speech Enhancement via Embeddings from Pre-trained Generative Audioencoders Interspeech 2025 DualSpeech: Enhancing Speaker-Fidelity and Text-Intelligibility Through Dual Classifier-Free Guidance Interspeech 2024