| 本文已被：浏览 5655次 下载 6416次 |
码上扫一扫！ |
|
|
| 基于邻接空间的鲁棒语音识别方法 |
|
严斌峰1,2, 朱小燕1, 张智江2, 张范2
|
|
1.清华大学,计算机科学与技术系,北京,100084;2.中国联合通信有限公司,北京,100032
|
|
| 摘要: |
| 提出了一种基于邻接空间模型的鲁棒语音识别方法,解决测试集和训练集差别导致的识别正确率过低的问题.在以声学模型为中心的邻接空间中计算贝叶斯预测概率密度值,作为观察概率输出分值进行识别.实验表明,相对于传统语音识别方法,鲁棒识别方法在保证干净测试集的识别率没有很大下降的前提下,对含噪测试集的识别率获得了较大的提高. |
| 关键词: 模型空间 声学模型 语音识别 贝叶斯预测密度 模式识别 |
| DOI： |
| 分类号: |
| 基金项目:Supported by the National Natural Science Foundation of China under Grant No.60272019(国家自然科学基金) |
|
| Robust Speech Recognition Based on Neighborhood Space |
|
YAN Bin-Feng,ZHU Xiao-Yan,ZHANG Zhi-Jiang,ZHANG Fan
|
| Abstract: |
| This paper presents an approach to robust speech recognition based on neighborhood space, which can achieve performance robustness under mismatch between training and testing conditions. This approach uses neighborhood space of each underlying model to produce Bayesian predictive density as observation probability density. Experimental results show that the proposed method improves the performance robustness. |
| Key words: model space acoustic model speech recognition Bayesian predictive density pattern recognition |
