通过解码器增强正则化，提升语音识别模型泛化能力。
Improving Automatic Speech Recognition with Decoder-Centric Regularisation in Encoder-Decoder Models
- 在解码器层引入辅助分类器，动态重估下一个词概率。
- 在AMI和Gigaspeech上分别降低2.7和2.9的错误率。
- 适合追求小模型高鲁棒性的语音识别研究者使用。
本文提出一种简单有效的编码器-解码器型自动语音识别（ASR）模型正则化方法，称为DeCRED，通过在解码器各层引入辅助分类器，提出两种重新估计下一个词概率的解码策略。基于近期的E-branchformer架构，构建的ASR系统在性能上与Whisper-medium相当，优于OWSM v3，且仅需少量训练数据和模型规模。在此强基线基础上，DeCRED进一步提升性能，并显著增强对域外场景的泛化能力：在AMI和Gigaspeech数据集上分别实现2.7和2.9的绝对错误率下降。论文提供了详尽的分析与实验验证所提正则化方案的有效性。
原文摘要 · Abstract (English)
This paper proposes a simple yet effective way of regularising the encoder-decoder-based automatic speech recognition (ASR) models that enhance the robustness of the model and improve the generalisation to out-of-domain scenarios. The proposed approach is dubbed as $\textbf{De}$coder-$\textbf{C}$entric $\textbf{R}$egularisation in $\textbf{E}$ncoder-$\textbf{D}$ecoder (DeCRED) architecture for ASR, where auxiliary classifier(s) is introduced in layers of the decoder module. Leveraging these classifiers, we propose two decoding strategies that re-estimate the next token probabilities. Using the recent E-branchformer architecture, we build strong ASR systems that obtained competitive WERs as compared to Whisper-medium and outperformed OWSM v3; while relying only on a fraction of training data and model size. On top of such a strong baseline, we show that DeCRED can further improve the results and, moreover, generalise much better to out-of-domain scenarios, where we show an absolute reduction of 2.7 and 2.9 WERs on AMI and Gigaspeech datasets, respectively. We provide extensive analysis and accompanying experiments that support the benefits of the proposed regularisation scheme.
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。