对比三种扩散模型语音识别解码策略，发现阈值法更快更准。
Decoding Strategies for Diffusion-Based ASR: A Systematic Evaluation of Confidence-Based Thresholding
- 用置信度阈值动态决定每轮生成多少词
- 静态阈值法速度更快，准确率接近传统方法
- 适合追求实时性的语音识别系统开发者
尽管基于大语言模型的自动语音识别（ASR）精度高，但其解码速度受限于自回归的顺序生成。扩散语言模型（DLM）提供了并行解码的替代方案，但在ASR中的解码策略仍不明确。本文系统评估了三种DLM-ASR解码策略：固定数量、静态置信度阈值和动态置信度阈值。通过负对数似然估计的不确定性来分析每轮解码进展，发现两种基于阈值的策略在准确率与速度之间表现更优。这一现象源于高置信度分布集中：多数词在早期就达到高置信度，可提前提交，低置信度词则推迟到后期处理。静态阈值策略在较低解码成本下实现接近自回归解码的准确率，显著提升效率。
原文摘要 · Abstract (English)
While LLM-based Automatic Speech Recognition (ASR) achieves high accuracy, its speed is limited by sequential autoregressive decoding. Diffusion Language Models (DLMs) offer a parallel alternative, yet their decoding strategies remain under-explored in ASR contexts. This paper analyzes three decoding schemes for DLM-based ASR: fixed-number, static confidence threshold, and dynamic confidence threshold. We introduce a round-wise analysis of decoding progress using Negative Log-Likelihood-based uncertainty as a proxy for prediction reliability. Our results show that both threshold-based strategies provide a better accuracy-speed trade-off than fixed-number schemes. This behavior is associated with the more concentrated confidence distribution observed in the evaluated ASR settings: many tokens reach high confidence early, enabling multiple tokens to be committed in early decoding rounds while lower-confidence tokens are deferred to later rounds. The static-threshold strategy achieves accuracy close to autoregressive decoding at lower decoding cost.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。