本论文研究复杂强背景噪声下的语音信号检测问题。
This dissertation focuses on the voice activity detection problem under adverse background noise.
为此，首先、也是关键要解决的技术之一就是必须实现噪声环境下语音信号起点的可靠检测。
As the result, the first and one of the most important tasks is to detect the jumping-off point of speech signals reliably under noisy environments.
在较低信噪比情况下，基于语音信号的短时相对自相关序列的短时平均幅度的端点检测能够获得较高的检测精度。
The endpoint detection based on short-time average magnitude of speech signals relative autocorrelation sequences can be detected in high accuracy under the low signal-to noise ratio.
本文通过对语音信号产生机制的分析，将分形维方法用于普通话孤立词语音信号起止端点的检测。
Based on analyses to the generation mechanism of speech signals, this paper presents a novel method which USES fractal dimension to determine speech terminals for mandarin isolated words.
语音信号的三阶累积量通常不等于零，因而可以用来检测噪声环境中语音的起始点和终止点。
Third-order cumulants of speech signals are not identically zero, so it could be used to detect the start point and end point of the voice under very noisy environments.
对语音信号端点检测的主要方法，如基于短时能量的方法、基于HMM的方法、基于自相关相似距离的方法等进行了深入研究。
The main speech signal endpoint detection methods, such as short time energy based scheme, HMM based scheme, related alike scheme and so on are investigated deeply.
将声门闭合在语音信号中表现出相应的奇异性，与图像边缘的灰阶突变进行等价对比，直接将小波变换用于声门闭合奇异型的检测，并不会得到预期效果。
If the wavelet transform is directly implemented in pitch detection, comparing the glottal closure singularity of speech signal with image grey break, we will not obtain the anticipative result.
语音信号的端点检测技术就是从包含语音的一段信号中准确地确定语音的起始点和终止点，区分语音和非语音信号。
The endpoint detection technology of speech signal is to accurately determine starting point and ending point from a section of speech signal. Thus it can distinguish speech and non-speech signal.
自相关基音检测算法是语音信号处理的关键技术，算法的效率直接影响语音信号实时处理的质量。
The autocorrelation pitch detection algorithm is the key technique for speech signal processing, and its efficiency directly affects the quality of real-time speech processing.
语音分离的研究在语音通信、声学目标检测、声音信号增强等方面有着重要的理论意义和实用价值。
Separation of speech in voice communications, acoustic target detection, sound signal enhancement, and so has important theoretical significance and practical value.
自相关基音检测算法是语音信号处理的关键技术，算法的效率直接影响了语音信号实时处理的质量。
In speech signal processing, one of the key technologies is the pitch detection algorithm, and its efficiency directly affects the quality of speech's real-time processing.
在众多语音信号处理应用领域，语音检测技术有非常重要的意义。
So voice activity detection is very important in many speech application fields.
实验证明，该算法在低信噪比的情况下，能够准确的检测出语音信号的端点。
The experiments show that this algorithm can detect speech endpoint accurate as low SNR.
实验表明这种方法计算复杂度较低，而且在低信噪比的情况下仍能较好的检测到语音信号的端点。
The complexity of this method is lower than some currently algorithm and can detect effectively speech endpoint.
根据语音信号产生机理，结合常用的线性预测和最大似然法，提出了一种有效的基音检测算法。
According to the mechanism of speech signal, an effective pitch detection algorithm by combined liner predictive coding with maximum likelihood is proposed.
本文提出了一种在混叠语音信号中检测各自语音分量基音信息的方法。
This paper puts up a method suitable for multi pitch detecting under overlapping speech signals environment.
本文首先总结了语音信号数字化处理过程，分析了常用的几种端点检测方法，并给出了其实验结果与一些相应的改进。
Firstly, the digital speech signal processing and some common speech endpoint detection methods are summarized and analysed. Some experiment results and improvements are also shown in the paper.
如果检测存在语音信号则通过DA把语音转换输出。
Ifspeech signal is detected, then it can be transformed to output through DA.
如果检测存在语音信号则通过DA把语音转换输出。
Ifspeech signal is detected, then it can be transformed to output through DA.
应用推荐