通过解码器中心正则化提升语音识别模型鲁棒性，效果显著。
DeCRED: Decoder-Centric Regularization for Encoder-Decoder Based Speech Recognition
- 在解码器中加入辅助分类器，实现中间状态的词元预测。
- 跨7个域内测试集降低36.6%语言模型困惑度，平均误识率下降0.1%。
- 适用于小数据、低参数场景，适合追求高效部署的语音识别应用。
本文提出一种简单而有效的编码器-解码器语音识别模型内部语言模型正则化方法——解码器中心正则化（DeCRED）。该方法在解码器中添加辅助分类器，利用中间特征进行下一个词元的预测。实验表明，DeCRED 在11个测试集上使内部语言模型的BPE困惑度相对降低36.6%。在5个域内与3个域外测试集中，均实现实际字错率（WER）的改进：域内平均从6.4%降至6.3%，域外从18.2%降至16.2%。在TEDLIUM3数据集上达到7.0% WER，优于基线和编码器中心的InterCTC正则化0.6%与0.5%。尽管训练数据更少、参数更少，其性能仍与OWSM v3.1和Whisper-medium相当。
原文摘要 · Abstract (English)
This paper presents a simple yet effective regularization for the internal language model induced by the decoder in encoder-decoder ASR models, thereby improving robustness and generalization in both in- and out-of-domain settings. The proposed method, Decoder-Centric Regularization in Encoder-Decoder (DeCRED), adds auxiliary classifiers to the decoder, enabling next token prediction via intermediate logits. Empirically, DeCRED reduces the mean internal LM BPE perplexity by 36.6% relative to 11 test sets. Furthermore, this translates into actual WER improvements over the baseline in 5 of 7 in-domain and 3 of 4 out-of-domain test sets, reducing macro WER from 6.4% to 6.3% and 18.2% to 16.2%, respectively. On TEDLIUM3, DeCRED achieves 7.0% WER, surpassing the baseline and encoder-centric InterCTC regularization by 0.6% and 0.5%, respectively. Finally, we compare DeCRED with OWSM v3.1 and Whisper-medium, showing competitive WERs despite training on much less data with fewer parameters.
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。