论文标题
内部语言模型估计基于自适应语言模型融合域适应性
Internal Language Model Estimation based Adaptive Language Model Fusion for Domain Adaptation
论文作者
论文摘要
ASR模型部署环境正在发生变化，并且可以在会话期间跨不同域切换传入的语音。当仅目标域文本数据可用时，这给有效域的适应带来了挑战，我们的目标是在目标域上明显提高性能，而通用域上的性能则较小。在本文中，我们提出了一种自适应LM融合方法，称为内语言模型估计基于自适应域的适应性（ILME-ADA）。为了实现这种ILME-ADA，根据内部LM和外部LM和外部LM（ELM）的最高分数计算了插值的对数似然分数。我们证明了所提出的ILME-ADA方法与RNN-T和LAS建模框架的疗效分别在两个域特异性（目标）测试集上，分别使用神经网络和N-Gram LMS作为ELMS。与基于浅层和ILME的LM Fusion方法相比，所提出的方法在目标测试集上的性能上可以显着更好，而在一般测试集上的性能降低最小。
ASR model deployment environment is ever-changing, and the incoming speech can be switched across different domains during a session. This brings a challenge for effective domain adaptation when only target domain text data is available, and our objective is to obtain obviously improved performance on the target domain while the performance on the general domain is less undermined. In this paper, we propose an adaptive LM fusion approach called internal language model estimation based adaptive domain adaptation (ILME-ADA). To realize such an ILME-ADA, an interpolated log-likelihood score is calculated based on the maximum of the scores from the internal LM and the external LM (ELM) respectively. We demonstrate the efficacy of the proposed ILME-ADA method with both RNN-T and LAS modeling frameworks employing neural network and n-gram LMs as ELMs respectively on two domain specific (target) test sets. The proposed method can achieve significantly better performance on the target test sets while it gets minimal performance degradation on the general test set, compared with both shallow and ILME-based LM fusion methods.
