RubatoCodec: Budgeted Adaptive Speech Tokenization with Streaming Decoding
Neural speech codecs provide discrete tokens for speech generation. Lower frame rates shorten token sequences, but each token must then carry more linguistic and acoustic information. Variable-frame-rate codecs address this trade-off by adapting token allocation to speech content, but threshold-based allocation lets content determine the token count, so the sequence length a speech generator must produce varies across utterances and datasets at a fixed setting. We present RubatoCodec, a variable-frame-rate speech codec built on X-Codec-2 with an exact utterance-level event budget and streaming decoding. Its Adaptive Firing mechanism uses changes in codec features and waveform spectra to divi
| Authors | Chihiro Arata, Shohei Taniguchi, Gouki Minegishi et al. |
|---|---|
| Primary category | |
| Published | 21 October 2026 |
| Last updated at source | — |
Connected in the knowledge graph
- third-intelligence/RubatoCodecModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 22 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.