Cepstral gain normalization for noise robust speech recognition
Cepstral gain normalization for noise robust speech recognition
复制标题
DOI：
10.1109/icassp.2004.1325959
复制
发表时间：
2004-05
期刊：
影响因子：
--
通讯作者：
S. Yoshizawa;N. Hayasaka;N. Wada;Y. Miyanaga
中科院分区：
文献类型：
--
作者：
S. Yoshizawa;N. Hayasaka;N. Wada;Y. Miyanaga
本文介绍了一种鲁棒的语音识别技术，它归一化倒谱增益，以消除加性噪声的影响。我们假设这种效应可以用对数谱中的增益和直流分量组成的近似模型来表示。因此，我们提出了倒谱增益归一化（CGN），通过计算语音帧中倒谱系数的最大值和最小值来归一化增益。由于该方法同时适用于训练数据和测试数据，因此无需先验知识和环境适应性，即可提取噪声鲁棒特征。我们已经评估了噪声环境下使用Noisex-92数据库和100个日本城市名称的任务识别性能。与传统方法的组合相比，CGN在各种SNR下提高了识别准确度。
The paper describes a robust speech recognition technique which normalizes cepstral gains in order to remove effects of additive noise. We assume that the effects can be expressed by an approximate model which consists of gain and DC components in log-spectrum. Accordingly, we propose cepstral gain normalization (CGN) which normalizes the gains by means of calculating maximum and minimum values of cepstral coefficients in speech frames. The proposed method can extract noise robust features without a priori knowledge and environmental adaptation because it is applied to both training and testing data. We have evaluated recognition performance under noisy environments using the Noisex-92 database and a 100 Japanese city names task. The CGN provides improvements of recognition accuracy at various SNRs compared with combinations of conventional methods.