为提高语音端点检测系统在低信噪(0 dB 以下) 下 检测的准确率, 提出了一种基于谱熵的端点检测算法。将每 帧信号分为16 个子带, 选取频谱分布在250～ 3. 5 kHz 并且 能量不超过该帧总能量90 的子带, 计算经过语音增强后的 子带能量以及各子带信噪比, 根据各子带信噪比的不同调整 其在整个谱熵计算过程中的权重, 然后平滑谱熵, 以最终的 谱熵作为端点检测的依据-To improve endpoint detection system in the low

KEY FEATURES Resolution of 230,000 Counts (Peak-to-Peak) Offset Drift: 5 nV/8C Gain Drift: 2 ppm/8C Line Frequency Rejection: >150 dB Buffered Differential Inputs Programmable Filter Cutoffs Speci Two-Channel Programmable Gain Fron

KEY FEATURES Resolution of 230,000 Counts (Peak-to-Peak) Offset Drift: 5 nV/8C Gain Drift: 2 ppm/8C Line Frequency Rejection: >150 dB Buffered Differential Inputs Programmable Filter Cutoffs Specified for Drift Over Timeh RefGHGJGere