Paper Detail
Yingzhuo Deng, Chong Li, Bingxin Liu, Yi Shu, Tianyu Peng, Can Xie, Siyao Song, Shuo Ren, Jiajun Zhang
Spoken Dialogue Models (SDMs) typically share a speech-token space for generation and synthesis, leading to long autoregressive sequences and costly inference. Lower-rate speech tokenizers shorten sequences but may introduce compression-quality trade-offs and costly replacement without breaking this coupling. To address this limitation, we propose CoSTA, a compatibility-preserving post-hoc framework that decouples generation and synthesis token spaces while retaining the original speech tokenizer and decoder. CoSTA extends the generation token space with compressed representations via mean-initialized vocabulary extension, pronunciation adaptation, and dialogue adaptation, followed by deterministic expansion back to the original speech-token space before synthesis. On bilingual speech-dialogue benchmarks, CoSTA achieves approximately 1.7times expanded speech-token generation speed, lower full-response latency, and higher throughput while preserving response quality. Analyses show more sustained interaction under limited budgets and a practical trade-off among compression, decoding efficiency, and quality. Further experiments demonstrate cross-architecture transfer and complementarity to low-rate tokenization.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{deng2026costa,
title = {CoSTA: Compressed Speech Token Adaptation for Efficient Spoken Dialogue Models},
author = {Yingzhuo Deng and Chong Li and Bingxin Liu and Yi Shu and Tianyu Peng and Can Xie and Siyao Song and Shuo Ren and Jiajun Zhang},
year = {2026},
abstract = {Spoken Dialogue Models (SDMs) typically share a speech-token space for generation and synthesis, leading to long autoregressive sequences and costly inference. Lower-rate speech tokenizers shorten sequences but may introduce compression-quality trade-offs and costly replacement without breaking this coupling. To address this limitation, we propose CoSTA, a compatibility-preserving post-hoc framework that decouples generation and synthesis token spaces while retaining the original speech tokenize},
url = {https://huggingface.co/papers/2610.21143},
keywords = {Spoken Dialogue Models, speech-token space, autoregressive sequences, speech tokenizers, CoSTA, vocabulary extension, pronunciation adaptation, dialogue adaptation, cross-architecture transfer, low-rate tokenization, code available, huggingface daily},
eprint = {2610.21143},
archiveprefix = {arXiv},
}
{}