Year: 2026
Type: preprint
Abstract: We propose 21Codec, a streaming codec model with reduced recoverable speaker information from the token stream and decoder-side speaker control. Existing codec models infer speaker identity from token stream. Making them streamable is not sufficiently robust to speaker drift, because each chunk re-infers the identity from the local chunk context alone. Our adversarial speaker classifier and NANSY-style formant-shift data augmentation pushes the model to rely on the provided speaker embedding while reducing the recoverable speaker information from the token stream. We show that 21Codec can control speaker identity through the conditioning vector, and that the speaker identity is maintained across chunks during streaming. With the ability to control speaker identity even in mid-stream, 21Codec is a promising candidate for streaming TTS systems for better controllability of speaker identity.
Source: arXiv (Cornell University)
Institution: Leiden University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Keyword: speaker embedding
Open Access status: green
OpenAlex ID: W7236685668
