特征参数的选取对整个语音识别系统的实时性、鲁棒性有很大的影响。
The chosen speech feature parameters have great effects on robustness and real-time of the speech recognition system.
发现了一种新颖的鲁棒特征参数-自适应子带谱熵(aspse)，它能成功地在不同的背景噪声下检测语音端点。
Finally, a novel robust feature parameter, Adaptive Subband Power Spectral Entropy (ASPSE), is presented to successfully detect endpoints in different background noises.
应用推荐