A New Feature Normalization Scheme Based on Eigenspace for Noisy Speech Recognition

机译：基于特征空间的噪声语音识别新特征归一化方案

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

We propose a new feature normalization scheme based on eigen-space, for achieving robust speech recognition. In particular, we employ the Mean and Variance Normalization (MVN) in eigenspace using unique and independent eigenspaces to cepstra, delta and delta-delta cepstra respectively. We also normalize training data in eigenspace and get the model from the normalized training data. In addition, a feature space rotation procedure is introduced to reduce the mismatch of training and test data distribution in noisy condition. As a result, we obtain a substantial recognition improvement over the basic eigenspace normalization.

机译：我们提出了一种基于特征空间的新特征归一化方案，以实现鲁棒的语音识别。特别是，我们在特征空间中采用均值和方差归一化（MVN），分别使用独特和独立的特征空间分别对倒谱，δ和δ-δ倒谱。我们还对特征空间中的训练数据进行归一化，并从归一化的训练数据中获得模型。另外，引入了特征空间旋转程序以减少在嘈杂条件下训练和测试数据分布的不匹配。结果，我们在基本特征空间归一化方面获得了实质性的改进。

著录项

来源
《International Conference on String Processing and Information Retrieval(SPIRE 2004); 20041005-08; Padova(IT)》|2004年|P.76-78|共3页
会议地点 Padova(IT)
作者
Yoonjae Lee; Hanseok Ko;
展开▼
作者单位

Dept. of Electronics and Computer Engineering, Korea University, Seoul, Korea;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类数据备份与恢复;
关键词

相似文献

外文文献
中文文献
专利

1. Normalized Autocorrelation based Features for Robust Speech Recognition in Context with Noisy Environment [J] . Poonam Bansal, Amita Dev, Shail Bala Jain Journal of information and computing science . 2011,第1期

机译：噪声环境下基于归一化自相关的鲁棒语音识别特征
2. IMPROVING EIGENSPACE-BASED FUZZY LOGIC SYSTEM USING A LINEAR INTERPOLATION SCHEME FOR SPEECH PATTERN RECOGNITION [J] . Ing-Jr Ding, Chih-Ta Yen Transactions of the Canadian Society for Mechanical Engineering . 2013,第3期

机译：使用线性插值方案改进基于特征空间的语音图形识别
3. Autocorrelation-based noise subtraction method with smoothing, overestimation, energy, and cepstral mean and variance normalization for noisy speech recognition [J] . Gholamreza Farahani EURASIP journal on audio, speech, and music processing . 2017,第1期

机译：基于自相关的噪声减法，具有平滑，高估，能量，倒谱均值和方差归一化的功能，可用于嘈杂的语音识别
4. A New Feature Normalization Scheme Based on Eigenspace for Noisy Speech Recognition [C] . Yoonjae Lee, Hanseok Ko International Conference on String Processing and Information Retrieval . 2004

机译：基于噪声语音识别的eigenspace的新功能规范化方案
5. Duration normalization for robust recognition of spontaneous speech via missing feature methods. [D] . Nedel, Jon P. 2004

机译：持续时间归一化，可通过缺失特征方法对自发语音进行可靠识别。
6. Particle Swarm Optimization Based Feature Enhancement and Feature Selection for Improved Emotion Recognition in Speech and Glottal Signals [O] . Hariharan Muthusamy, Kemal Polat, Sazali Yaacob -1

机译：基于粒子群优化的特征增强和特征选择用于语音和声门信号中的情感识别
7. A New Feature Normalization Scheme Based on Eigenspace for Noisy Speech Recognition [O] . Yoonjae Lee, Hanseok Ko 2015

机译：一种基于特征空间的带噪语音识别新特征规划方案

A New Feature Normalization Scheme Based on Eigenspace for Noisy Speech Recognition

摘要

著录项

相似文献

相关主题

期刊订阅