A maximum likelihood (ML) linear regression (LR) solution to environment normalization is provided where the environment is modeled as a hidden (non-observable) variable. By application of an expectation maximization algorithm and extension of Baum-Welch forward and backward variables (Steps 23a–23d) a source normalization is achieved such that it is not necessary to label a database in terms of environment such as speaker identity, channel, microphone and noise type.
展开▼
机译:提供了环境标准化的最大似然(ML)线性回归(LR)解决方案,其中将环境建模为隐藏(不可观察)变量。通过应用期望最大化算法并扩展Baum-Welch前向和后向变量(步骤 23 B> a – I> 23 B> d I>)实现了源规范化,因此无需根据环境(例如说话者身份,声道,麦克风和噪声类型)标记数据库。
展开▼