让语音与文本长度对齐，提升端到端语音识别精度
End-to-end Speech Recognition with similar length speech and text
- 设计时间无关损失和基于编辑距离的对齐交叉熵损失
- 在AISHELL数据集上帧数减少至少86%且识别准确率更高
- 适合追求高效低延迟语音识别的场景
语音与文本长度不匹配是自动语音识别中的挑战。以往研究采用连接时序分类（CTC）等方法对齐，但传统方法在将语音下采样至接近文本长度时效果不佳。本文聚焦于语音与文本长度相近的情况，提出两种对齐方法：时间无关损失（TIL）和基于编辑距离的对齐交叉熵损失（AXE）。为增强关键帧信息，引入帧融合机制，对关键帧及其前后各2帧加权求和。在AISHELL-1和AISHELL-2数据集子集上的实验表明，所提方法优于先前工作，在保证性能的同时使帧数减少至少86%。
原文摘要 · Abstract (English)
The mismatch of speech length and text length poses a challenge in automatic speech recognition (ASR). In previous research, various approaches have been employed to align text with speech, including the utilization of Connectionist Temporal Classification (CTC). In earlier work, a key frame mechanism (KFDS) was introduced, utilizing intermediate CTC outputs to guide downsampling and preserve keyframes, but traditional methods (CTC) failed to align speech and text appropriately when downsampling speech to a text-similar length. In this paper, we focus on speech recognition in those cases where the length of speech aligns closely with that of the corresponding text. To address this issue, we introduce two methods for alignment: a) Time Independence Loss (TIL) and b) Aligned Cross Entropy (AXE) Loss, which is based on edit distance. To enhance the information on keyframes, we incorporate frame fusion by applying weights and summing the keyframe with its context 2 frames. Experimental results on AISHELL-1 and AISHELL-2 dataset subsets show that the proposed methods outperform the previous work and achieve a reduction of at least 86\% in the number of frames.
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。