用动态词汇提升语音识别罕见词准确率，同时加快推理速度。
DYNAC: Dynamic Vocabulary based Non-Autoregressive Contextualization for Speech Recognition
- 将动态词汇嵌入CTC模型中间层，实现非自回归推理
- 在LibriSpeech测试集上实时因子降低81%，错误率仅降0.1点
- 适合需要快速响应的语音识别场景，如实时字幕生成
上下文偏置（CB）能提升语音识别中罕见和未见短语的性能。近期研究引入动态词汇，在自回归模型中以可扩展标记表示上下文短语，虽提高准确性但推理慢。尽管动态词汇可应用于非自回归模型（如连接时序分类CTC），但其条件独立假设无法捕捉静态与动态标记间的依赖关系。本文提出DYNAC（基于动态词汇的非自回归上下文建模），一种自条件化CTC方法，将动态词汇融入编码器中间层。通过使编码器依赖动态词汇，DYNAC有效捕获静态与动态标记间依赖关系，同时降低实时因子（RTF）。实验表明，在LibriSpeech 960测试-干净集上，DYNAC将RTF降低81%，仅带来0.1个百分点的词错误率（WER）上升。
原文摘要 · Abstract (English)
Contextual biasing (CB) improves automatic speech recognition for rare and unseen phrases. Recent studies have introduced dynamic vocabulary, which represents context phrases as expandable tokens in autoregressive (AR) models. This method improves CB accuracy but with slow inference speed. While dynamic vocabulary can be applied to non-autoregressive (NAR) models, such as connectionist temporal classification (CTC), the conditional independence assumption fails to capture dependencies between static and dynamic tokens. This paper proposes DYNAC (Dynamic Vocabulary-based NAR Contextualization), a self-conditioned CTC method that integrates dynamic vocabulary into intermediate layers. Conditioning the encoder on dynamic vocabulary, DYNAC effectively captures dependencies between static and dynamic tokens while reducing the real-time factor (RTF). Experimental results show that DYNAC reduces RTF by 81% with a 0.1-point degradation in word error rate on the LibriSpeech 960 test-clean set.
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。