Generalized Variable Parameter HMMs for Noise Robust Speech Recognition
Generalized Variable Parameter HMMs for Noise Robust Speech Recognition
复制标题
DOI：
10.21437/interspeech.2011-201
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
Ning Cheng;Xunying Liu;Lan Wang
中科院分区：
文献类型：
--
作者：
Ning Cheng;Xunying Liu;Lan Wang
处理可变环境噪声是自动语音识别（ASR）系统的一项具有挑战性的任务。为了解决这个问题，可以使用使用在不同噪声环境中收集的语音数据的多风格、噪声条件无关（CI）模型训练或不确定性解码技术。另一种方法是例如使用可变参数HMM（VP-HMM）来针对变化的噪声水平显式地近似高斯分量均值和方差参数的连续轨迹。本文研究了一种更一般化的变参数隐马尔可夫模型（GVP-HMM）。除了高斯分量均值和方差之外，它还可以为绑定线性变换提供更紧凑的轨迹建模。另一种噪声条件相关（CD）训练算法也被提出来处理训练噪声条件分布的偏差。一致的错误率增益，获得了传统的VP-HMM的平均值和方差的轨迹建模中词汇普通话中文车载导航命令识别任务。
Handling variable ambient noise is a challenging task for automatic speech recognition (ASR) systems. To address this issue, multi-style, noise condition independent (CI) model training using speech data collected in diverse noise environments, or uncertainty decoding techniques can be used. An alternative approach is to explicitly approximate the continuous trajectory of Gaussian component mean and variance parameters against the varying noise level, for example, using variable parameter HMMs (VP-HMM). This paper investigates a more generalized form of variable parameter HMMs (GVP-HMM). In addition to Gaussian component means and variances, it can also provide a more compact trajectory modelling for tied linear transformations. An alternative noise condition dependent (CD) training algorithm is also proposed to handle the bias to training noise condition distribution. Consistent error rate gains were obtained over conventional VP-HMM mean and variance only trajectory modelling on a medium vocabulary Mandarin Chinese in-car navigation command recognition task.