A flexible framework for HMM based noise robust speech recognition using generalized parametric spac

来源 :Science China(Information Sciences) | 被引量 : 0次 | 上传用户:rrttwytpic
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
Handling variable, non-stationary 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 hidden Markov model (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 modeling 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 modeling on a media vocabulary Mandarin Chinese in-car navigation command recognition task. Handling variable, non-stationary 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, 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 hidden Markov model (VP-HMM). This paper investigates a more generalized form In addition to Gaussian component means and variances, it can also provide a more compact trajectory modeling 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 onl y trajectory modeling on a media vocabulary Mandarin Chinese in-car navigation command recognition task.
其他文献
本文介绍了2005现场流行病学的研究进展,介绍了现场流行病学的概念和方法学的研究情况,介绍了现场流行病学的学科体系与应用培训,分析了美国流行病学能力评估结果对现场流行病学
目的分析云南省2011-2015年含麻疹成分疫苗(Measles containing vaccine,MCV)疑似预防接种异常反应(Adverse events following immunization,AEFI)发生特征和预防接种安全性
近两年来,世界各大铁氧体公司竞相提高锰锌铁氧体材料技术性能,以适应日益拓展的应用领域,使这种基础功能材料的发展出现了勃勃生机.在IT产业、电力电子,特别是网络通信等用
会议
中国是造纸发源地,由于历史原因,我国造纸制浆设备及工艺没有占据国际第一位置,但国际上许多国家在中国古老造纸制浆工艺基础上发展了针叶、阔叶木等为原料的造纸制浆工艺,并
应用于笔记本电脑、数码相机,LCD背光源等的器件对磁芯要求小型化的同时,又要求磁芯的工作温度向低温方向移动.传统的材料开发采用对照的实验方法,对实验结果进行分析后再进
会议
我国信托业自1979年恢复以来,由于受人文环境、市场基础、制度体系等外部因素困扰,呈现出了制度滞后、品种单一、竞争环境不规范等一系列制约发展的问题。为此,有必要通过强
目前情况浙江天通电子股份有限公司经过第十个五年计划(2001-2005),已取得巨大进步,已发展成为拥有近3000名员工,超十亿元净资产的中国首家自然人直接控股的上市公司,成为集
会议
一般而言,新材料的研制大多来自于新兴电子器件、设备的需求,对于磁性材料也有类似情况.近年来,随着各类变压器及电子设备对MnZn铁氧体材料技术的不断需求,功率铁氧体材料的
会议
宽带接入技术的迅速发展对铁氧体电感元件提出各种新要求.本文叙述在宽带数字用户线中使用的电感元件和新开发的铁氧体材料。
滤波技术在抗EMI(电磁干扰)中有着非常重要的地位,其主要作用是滤除系统内外的电磁杂波.我们研制的小型化EMI直流电源滤波器就是使用在通信电源系统中抑制电磁干扰,提高控制