Novel Active Learning Method for Speech Recognition

作者：Liu Gang^*; Chen Wei; Guo Jun

来源：China Communications, 2010, 7(5): 29-39.

• active learning
• acoustic model
• speech recognition
• KLD
• confusion network

In speech recognition, acoustic modeling always requires tremendous transcribed samples, and the transcription becomes intensively time-consuming and costly. In order to aid this labor-intensive process, Active Learning (AL) is adopted for speech recognition, where only the most informative training samples are selected for manual annotation. In this paper, we propose a novel active learning method for Chinese acoustic modeling, the methods for initial training set selection based on Kullbaek-Leibler Divergence (KLD) and sample evaluation based on multi-level confusion networks are proposed and adopted in our active learning system, respectively. Our experiments show that our proposed method can achieve satisfying performances.

• 出版日期2010-11
• 单位北京邮电大学