Speaker Adaptation Techniques for Automatic Speech Recognition

摘要：

Statistical speech recognition using continuousdensity hidden Markov models (CDHMMs) has yielded many practical applications. However, in general, mismatches between the training data and input data significantly degrade recognition accuracy. Various acoustic model adaptation techniques using a few input utterances have been employed to overcome this problem. In this article, we survey these adaptation techniques, including maximum a posteriori (MAP) estimation, maximum likelihood linear regression (MLLR), and eigenvoice.

作者: Koichi Shinoda

作者单位: Tokyo Institute of Technology, Tokyo, Japan

会议类型: 国际会议

会议名称: 2011亚太信号与信息处理协会年度峰会(APSIPAASC 2011)

会议地点: 西安

会议语种:英文

页码: 1-8

在线出版日期: 2011-10-18（万方平台首次上网日期，不代表论文的发表时间）