← 研踪 PaperTrailarXiv:2611.24094 · v1
21Codec: Decoder-side Speaker Control for Text-to-Speech
首次提交 2026-11-18 17:19
版本更新 2026-11-18 17:19
雷达观测 2026-11-19 19:07
摘要
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.
作者备注:Submitted to ICASSP 2027
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-18 17:19 · 最新观测版本
21Codec: Decoder-side Speaker Control for Text-to-Speech
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.
查看此版本解读 →查看此版本原文 ↗