Spoken Language Models that Think Aloud

2026-09-22

AI Summary

为解决链式思维在口语模型中引入长时间沉默的问题，提出了一种异步边想边说框架，在保持推理准确性的同时减少用户可感知的沉默时间。

Abstract

While Chain-of-Thought (CoT) reasoning has improved the capability of language models, directly applying it to Spoken Language Models (SLMs) may introduce long silent intervals under the serial "think-then-speak" paradigm, disrupting real-time spoken interaction. To address this issue, we propose an asynchronous think-aloud framework for reasoning-based SLMs within the Thinker-Talker architecture. The framework maintains a primary reasoning stream for logical deduction and a lightweight think-aloud stream that generates short, task-grounded progress utterances conditioned on the user input and the evolving reasoning state. A dynamic balance strategy coordinates the two streams at runtime, triggering additional think-aloud speech to avoid silent gaps and canceling pending utterances when the final response becomes ready. Experiments on spoken reasoning and question-answering benchmarks show that our approach substantially reduces user-audible silence during reasoning while maintaining answer accuracy comparable to that of a serial "think-then-speak" baseline, demonstrating the potential of asynchronous think-aloud for responsive interaction in SLMs.

Problem

• Spoken Language Models
• Chain-of-Thought
• real-time interaction

Innovation

• asynchronous think-aloud framework
• Spoken Language Models (SLMs)
• dynamic balance strategy
• think-then-speak