This paper describes the effect of additive noise and convolution noise on speech data and gives a blind environmental compensation method to improve environmental robustness.
本文讨论了环境加性噪声和卷积噪声对语音数据的影响，以及提高系统的鲁棒性的盲的环境补偿方法。
ANN is widely used in speech recognition field due to its self adapting, parallelism, non-linearity, robustness and learning ability.
而人工神经网络以其自适应、并行性、非线性、鲁棒性和学习特性被广泛应用于语音识别领域。
The chosen speech feature parameters have great effects on robustness and real-time of the speech recognition system.
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。
应用推荐