基于优化检测网络和MLP特征改进发音错误检测的方法

该文基于优化的检测网络和多层感知(multi-layerperception,MLP)特征,提出一种可以更加准确地检测出错误发音类型的方法。首先,从第二语言学习的语音库中提取出基本的发音规则以及组合的发音规则,并相应地计算它们发生的先验概率,再将这些具有先验概率的规则用于构建基于多发音的扩展检测网络。然后在检测过程中,引入基于发音特征的MLP特征来描述发音概率,替代了传统的语音声学特征。最后使用基于MLP特征的GMM-HMM框架从检测网络中识别出最可能的发音音素串。实验表明:该方法将音素识别正确率提高了3.11%,错误类型准确率提高了7.42%。     

基于交叉熵顺序统计滤波的语音端点检测算法

为提高语音端点检测在强噪声环境下的准确率,提出了一种基于交叉熵顺序统计滤波(OSF)的语音端点检测算法。该算法以子带交叉熵为语音/非语音的区分特征,首先将每帧语音的频谱划分成若干个子带,估计出每个子带能量与背景噪声之间的交叉熵,然后把相继若干帧的子带能量交叉熵经过一组顺序统计滤波器,最后根据各帧交叉熵的值对输入的语音进行分类。实验结果表明:该算法能够有效地区分语音和非语音。特别是在强噪声环境下依然能够保持很高的检测率,具有鲁棒性。通过实验结果比较,该算法在性能上优于最近提出的基于能量顺序统计滤波和单纯交叉熵判别的两种方法。     

English Speech Recognition System on Chip

An English speech recognition system was implemented on a chip,called speech system-on-chip (SoC).The SoC included an application specific integrated circuit with a vector accelerator to improve performance.The sub-word model based on a continuous density hidden Markov model recognition algorithm ran on a very cheap speech chip.The algorithm was a two-stage fixed-width beam-search baseline system with a variable beam-width pruning strategy and a frame-synchronous word-level pruning strategy to significantly reduce the recognition time.Tests show that this method reduces the recognition time nearly 6 fold and the memory size nearly 2 fold compared to the original system,with less than 1% accuracy degradation for a 600 word recognition task and recognition accuracy rate of about 98%.