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。
Experiments show that the new arithmetic not only has excellent effects on speech improvement but also has potential to improve robustness of a speaker recognition system in noisy environments.
实验结果表明，这种方法不仅有明显的语音增强效果，且应用于噪声环境下的说话人识别系统时，能够提高系统的鲁棒性。
So we focus on the study of pitch detection algorithms for noisy speech and strive to find algorithms with relatively good accuracy and robustness.
为此，本论文就含噪语音进行基音检测算法的研究，力求寻找准确性和鲁棒性都相对较好的基音检测算法。
Experimental result shows that LOPDI algorithm can greatly increase automatic speech recognition system's robustness against additive noise.
实验表明，LOPDI算法能够显著提高语音识别系统对加性噪声的鲁棒性。
It is proved that this method has good ability and high robustness, and that it is an effect method in speech segmentation.
利用新方法进行分段并测试其鲁棒性，实验证明新方法分段效果好且鲁棒性强，是一种有效的音素分段算法。
In the meantime, we evaluate and analyze objectively the robustness of the low bit rate speech coding algorithms with our own objective evaluating system of the speech quality.
并利用所构建的语音质量客观评价平台，对语音增强低速语音编码算法的抗背景噪声性能进行了客观评估与分析。
The experiment results indicate that this technique is provided with a good robustness and is fit for different sources of speech signal, such as speech in musical backgrounds.
实验结果表明，该编码方式具有很好的顽健性，适合于不同来源的语音信号，例如带背景音乐的语音。
In order to make the speech recognition system maintain the good performance under these noise conditions, we must use various methods to enhance the robustness of system.
为了使语音识别系统在不同噪声环境下仍能具有较好的性能，就需要采用各种方法来增强识别系统的鲁棒性。
CELP coders, due to its high quality of reconstructed speech and robustness against channel noise, have many applications in mobile communication, encrypted telephone and voice relay service etc .
CELP以其高质量的合成语音及优良的抗噪声和多次转接性能，在移动通信，保密电话和语音中继等中低速率上获得了广泛应用。
In this paper, we propose a new approach based on spectral entropy and spectral subtraction for noisy speech endpoint detection, and discriminative rules with robustness.
本文提出了基于谱熵和谱减法相结合的带噪语音端点检测改进算法以及端点检测的判决准则。
Therefore, the noise robustness is a very important part of speech recognition research.
因此，噪声鲁棒性一直是语音识别研究中一个非常重要的方面。
Therefore, the noise robustness is a very important part of speech recognition research.
因此，噪声鲁棒性一直是语音识别研究中一个非常重要的方面。
应用推荐