Skip to main content
Search

# 21Codec

1 related articles

Subscribe to updates
  1. arXiv

    21Codec moves speaker identity to the decoder: streaming voices stop drifting chunk to chunk, and can change mid-stream

    Neural codecs for streaming text-to-speech usually infer speaker identity from the discrete token stream, and chunked decoding re-infers it from each local chunk alone, so the voice drifts within one utterance. 21Codec suppresses speaker information in the tokens and instead conditions every frame on an external speaker embedding at the decoder, which holds identity during streaming and allows a speaker change mid-stream. On unseen speakers, re-voiced output sits closer to the reference speaker than to the source; the cost is a higher word error rate than the unconditional version.

You’re all caught up