机构地区: 东莞理工学院计算机学院计算机科学与技术系
出 处: 《现代计算机》 2008年第8期40-43,50,共5页
摘 要: 提出一种基于模板的动态补偿方案(PDC),用来改善移动环境下语音识别(ASR)的鲁棒性。在PDC中,定义一个带偏差的固定模板来纠正数据训练时的环境变量,假设数据训练是根据一组事先定义好的应用场景下得到的;在识别时,瞬时的偏差由几种可能的模板线性加权得到。为了快速估计加权值,提出了基于语音相关先验模板的贝叶斯学习过程(PDC-SPE)。室外环境下实验表明,PDC-SPE学习过程好于常规的补偿自适应方法,通过训练后系统的错误识别率有20-25%的相对减少。 Proposes a Pattern-based Dynamic Compensation(PDC) scheme to improve the robustness of ASR in mobile environments. In PDC, a distortion pattern-set is employed to normalize the environmental variations in training data according to a set of pre-defined application scenarios. At recognition time, instantaneous distortion is calculated as a linear combination of several possible patterns. To online estimate the combination weights robustly, a Bayesian learning process with Speech-conditioned Prior Evolution is introduced into PDC (PDCSPE).In outdoor experiments, the PDC-SPE method outperforms other commonly used compensation/adaptation methods and leads to 20-25% relative reduction in Word Error Rate (WER) over a well-trained baseline system.
领 域: [自动化与计算机技术] [自动化与计算机技术] [化学工程]