Smoothing Method for Improved Minimum Phone Error Linear Regression
スポンサーリンク
概要
- 論文の詳細を見る
A smoothing method for minimum phone error linear regression (MPELR) is proposed in this paper. We show that the objective function for minimum phone error (MPE) can be combined with a prior mean distribution. When the prior mean distribution is based on maximum likelihood (ML) estimates, the proposed method is the same as the previous smoothing technique for MPELR. Instead of ML estimates, maximum a posteriori (MAP) parameter estimate is used to define the mode of prior mean distribution to improve the performance of MPELR. Experiments on a large vocabulary speech recognition task show that the proposed method can obtain 8.4% relative reduction in word error rate when the amount of data is limited, while retaining the same asymptotic performance as conventional MPELR. When compared with discriminative maximum a posteriori linear regression (DMAPLR), the proposed method shows improvement except for the case of limited adaptation data for supervised adaptation.
- The Institute of Electronics, Information and Communication Engineersの論文
著者
-
PAN Fuping
Key Laboratory of Speech Acoustics and Content Understanding
-
ZHAO Qingwei
Key Laboratory of Speech Acoustics and Content Understanding
-
PAN Fuping
Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences
-
YAN Yonghong
College of Information and Electronics, Beijing Institute of Technology
-
QI Yaohui
College of Information and Electronics, Beijing Institute of Technology
-
GE Fengpei
Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences
関連論文
- Noise Robust Feature Scheme for Automatic Speech Recognition Based on Auditory Perceptual Mechanisms
- A Forced Alignment Based Approach for English Passage Reading Assessment
- A Novel Discriminative Method for Pronunciation Quality Assessment
- Discriminative Approach to Build Hybrid Vocabulary for Conversational Telephone Speech Recognition of Agglutinative Languages
- Smoothing Method for Improved Minimum Phone Error Linear Regression