用CTC生成的初始序列，通过两步编辑实现高效语音识别。
CTC-Seeded Token Edit Refinement for Non-Autoregressive Speech Recognition
- 以CTC的输出为起点，直接预测插入、删除、替换操作来修正文本。
- 仅需两步编辑，词错误率（WER）显著降低，且可进一步提升。
- 适合追求快速推理与高精度的非自回归语音识别场景。
非自回归自动语音识别（ASR）支持并行解码，但许多基于精炼的方法从随机、完全掩码或固定长度的词元序列开始，需多次迭代重建完整转录。本文将ASR解码建模为对贪心连接时序分类（CTC）假设的变长编辑精炼过程。一个声学条件的编辑流解码器直接作用于压缩后的CTC假设，平行预测插入、删除和替换操作。该编辑流解码器与CTC模型联合训练，采用连续时间离散扩散损失。推理时发现，仅需两步编辑即可显著降低词错误率（WER），且无分类器引导（CFG）能通过聚焦音频特征进一步提升识别质量。同时，利用CTC置信度约束编辑提议以提高准确性。消融实验验证了设计选择的有效性，而解码器预训练和预训练编码器的引入带来显著性能增益。
原文摘要 · Abstract (English)
Non-autoregressive automatic speech recognition (ASR) enables parallel decoding, but many refinement-based methods begin from random, fully masked, or fixed-length token sequences, requiring multiple iterations to reconstruct the complete transcript. We instead formulate ASR decoding as a variable-length edit refinement of a greedy connectionist temporal classification (CTC) hypothesis. An acoustic-conditioned Edit Flow decoder operates directly on the collapsed CTC hypothesis, predicting insertion, deletion, and substitution operations in parallel. The Edit Flow decoder is jointly trained with a CTC model using a continuous-time discrete diffusion loss. During inference, we find that just two edit steps yield substantial Word Error Rate (WER) reductions, and classifier-free guidance (CFG) further enhances recognition quality by focusing the model on audio features. We also constrain edit proposals using CTC confidence to improve accuracy. Finally, ablation studies validate our design choices, while decoder pretraining and pretrained encoder integration yield significant additional performance gains.
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。