Kraken: LLM-based Speech-to-Speech Translation via Low-bitrate VQ and Dual-path Source Conditioning
Paper recorded by Signals 4 on 2026-09-11 in cs.CL. Abstract reproduced from arXiv; link to the original below.
Published 2026-09-11 on arXiv · recorded by Signals 4 on 2026-09-14
Category: cs.CL · 自然语言处理 · first seen 2026-09-14
Abstract
Speech-to-speech translation (S2ST) has advanced significantly with speech LLMs, offering the potential for joint optimization and preserving non-linguistic information. However, these models struggle with predicting high-bitrate speech tokens in LLMs, and face the challenge of relying on S2ST training data with ideally aligned speaker identity and prosody. We propose using low-bitrate tokens base
Read on arXiv →
Cite this page: Kraken: LLM-based Speech-to-Speech Translation via Low-bitrate VQ and Dual-path Source Conditioning: the #54 most recent of 186 cs.CL papers we have recorded (as of 2026-09-11). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/kraken-llm-based-speech-to-speech-translation-via-low-bitrate-vq-and-dual-path-s.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable:
papers.json
Get 4 AI signals a day by email — free.
Get 4 AI signals a day by email — free