Discriminative maximum a posteriori for acoustic model adaptation

doi:10.11772/j.issn.1001-9081.2014.01.0265

Journal of Computer Applications ›› 2014, Vol. 34 ›› Issue (1): 265-269.DOI: 10.11772/j.issn.1001-9081.2014.01.0265

• Network and distributed techno • Previous Articles Next Articles

Discriminative maximum a posteriori for acoustic model adaptation

QI Yaohui¹,²,³,PAN Fuping³,GE Fengpei³,YAN Yonghong²,³

1.
2. College of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China;
3. Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China;

Received:2013-07-16 Revised:2013-09-08 Online:2014-02-14 Published:2014-01-01
Contact: QI Yaohui
Supported by:
National Natural Science Foundation

鉴别性最大后验概率声学模型自适应

齐耀辉¹,²,³,潘复平³,葛凤培³,颜永红²,³

1.
2. 北京理工大学信息与电子学院,北京 100081;
3. 中国科学院声学研究所中国科学院语言声学与内容理解重点实验室,北京 100190;

通讯作者: 齐耀辉
作者简介:齐耀辉(1978-),女,河北石家庄人,讲师,博士研究生,主要研究方向:大词表连续语音识别;潘复平(1977-),男,安徽阜阳人,副研究员,博士,主要研究方向:大词表连续语音识别、发音质量自动评估;葛凤培(1982-),女,河北保定人,助理研究员,博士,主要研究方向:大词表连续语音识别、发音质量自动评估;颜永红(1967-),男,江苏无锡人,研究员,博士生导师,博士,主要研究方向:大词表连续语音识别。
基金资助:
国家自然科学基金资助项目

Abstract

Abstract: For Minimum Phone Error based Maximum A Posteriori (MPE-MAP) adaptation, in order to accurately estimate the center of prior distribution and to improve the recognition performance, the Maximum Mutual Information based MAP (MMI-MAP) adaptation and H-criterion, which was the interpolation of MMI and Maximum Likelihood (ML) criterion, based on MAP (H-MAP) adaptation were used for the estimation of the center of prior distribution, which led to MMI-MAP prior based MPE-MAP (MPE-MMI-MAP) and H-MAP prior based MPE-MAP (MPE-H-MAP). The experimental results of task adaptation show that the two proposed methods both can obtain better recognition performance than MPE-MAP, MMI-MAP and MAP adaptation. MPE-MMI-MAP and MPE-H-MAP can obtain 3.4% and 2.7% relative improvement over MPE-MAP respectively.

Key words: Maximum A Posteriori (MAP), Discriminative MAP (DMAP), Maximum Mutual Information (MMI), Minimum Phone Error (MPE), acoustic model adaptation

摘要： 为了更加准确地估计最小音素错误最大后验概率(MPE-MAP)自适应算法中的先验分布中心,使自适应后的声学模型参数更为准确,从而提高系统的识别性能,分别采用最大互信息最大后验概率(MMI-MAP)自适应和基于最大互信息准则与最大似然准则相结合的H-criterion最大后验概率(H-MAP)自适应估计先验分布中心,提出了基于最大互信息最大后验概率先验的最小音素错误最大后验概率(MPE-MMI-MAP)和基于H-criterion最大后验概率先验的最小音素错误最大后验概率(MPE-H-MAP)算法。任务自适应实验结果表明,MPE-MMI-MAP和MPE-H-MAP算法的自适应性能均优于MPE-MAP、MMI-MAP和最大后验概率(MAP)自适应方法,分别比MPE-MAP相对提高3.4%和2.7%。

关键词: 最大后验概率, 鉴别性最大后验概率, 最大互信息, 最小音素错误, 声学模型自适应

CLC Number:

TN912.3

QI Yaohui PAN Fuping GE Fengpei YAN Yonghong. Discriminative maximum a posteriori for acoustic model adaptation[J]. Journal of Computer Applications, 2014, 34(1): 265-269.

齐耀辉潘复平葛凤培颜永红. 鉴别性最大后验概率声学模型自适应[J]. 计算机应用, 2014, 34(1): 265-269.

[1]	DING Jianli, HAN Yuchao, WANG Jialiang. Estimation method for RFID tags based on rough and fine double estimation [J]. Journal of Computer Applications, 2017, 37(9): 2722-2727.
[2]	HUANG Wenna, PENG Yaxiong, HE Song. Vocal effort in speaker recognition based on MAP+CMLLR [J]. Journal of Computer Applications, 2017, 37(3): 906-910.
[3]	Yi-yan WANG. Adaptive image denoising algorithm based on generalized variational model [J]. Journal of Computer Applications, 2009, 29(11): 3033-3036.
[4]	Jie Liu . Image segmentation algorithm based on grey model MRF [J]. Journal of Computer Applications, 2008, 28(3): 686-687.

Discriminative maximum a posteriori for acoustic model adaptation

鉴别性最大后验概率声学模型自适应

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 4

Recommended Articles

Metrics