TES-VC can change both the speaker's voice and the acoustic environment of an audio clip from text prompts while preserving the words, using retrieval of known timbre embeddings and latent diffusion trained on synthetic mixtures.
System Overview The proposed TES-VC model is trained on purely acoustic data (Figure 1(a)), and leverages text-guided control during infer- ence (Figure 1(b))
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
In This Environment, As That Speaker: A Text-Driven Framework for Multi-Attribute Speech Conversion
TES-VC can change both the speaker's voice and the acoustic environment of an audio clip from text prompts while preserving the words, using retrieval of known timbre embeddings and latent diffusion trained on synthetic mixtures.