噪

It overcames the shortcoming of the discontinuous character in hard-thresholding function and solves the problem of the permanent bias in soft- thresholding function.

仿真实验结果表明，采用新的阈值函数的去噪效果在信噪比增益和最小均方误差意义上均优于传统的软

The principles of suppressing random noises with K-L transformation in wavelet conversion domain are that 1 wavelet decomposition is carried out on seismic signals to form wavelet packet sections in time sharing and frequency division, 2 K-L transformation is utilized to remove noises on sections, and 3 the de-noise wavelet packet sections are reconstituted into seismic sections to remove random noises.

介绍了小波变换域K-L变换压制随机噪声的基本原理，即先将地震信号进行小波分解形成分时分频的小波包剖面，然后用K-L，变换对小波包剖面进行去噪，再将去噪后的小波包剖面重构回地震剖面，从而达到消除随机噪声的目的。

The realization of the invention greatly reduces the workload of document image denoising processing, and the invention has advantages of easy achievement method, easy software realization, capability of realizing balance between computing complexity and the denoising efficiency.

本发明的实现大大减少了文档影像降噪处理的工作量，实现的方法简便，易于软件实现，可以实现运算复杂度与降噪效率之间的平衡。

The main idea of this dissertation is as following sequence: disturbance signal denoising, transient harmonic measurement, disturbance online detection, and PQD data classification mining. Utilizing wavelet theory, Teager energy operator, and data mining technology, this dissertation presents a comprehensive and systematic study of PQD online detection and classification.

本文针对这两个核心问题，沿着"扰动信号去噪暂态谐波测量扰动在线检测扰动数据分类挖掘"这一技术主线，运用小波理论、Teager能量算子和数据挖掘技术，对电能质量扰动信号去噪、暂态谐波测量、扰动在线检测以及扰动数据分类挖掘进行了系统研究。

By analyzing the faultiness of the wavelet method used in processing signal denoise and detection of weak signal.

通过分析小波变换处理信号噪声的方法及其在微弱信号检测方面的不够完善之处，提出适合于极低信噪比条件下小波消噪法的信号检测原理和方法，即通过构造具有可调功能的阈值函数以及对小波分解系数处理方式的优化设计等方法，在强背景噪声中提取出微弱的信号特征信息，从而实现微弱信号的检测。

Simulation result proved that the wavelet method has better performance in removing the noise of FOG's output signal, and the accuracy of alignment and navigation can be improved.

研究表明，基于小波的去噪方法能够更好地估计光纤陀螺的输出信号，具有更为理想的去噪效果，有效地解决了对准与导航过程中光纤陀螺噪声的影响，提高了对准与导航的精度。

In the paper, based on the analysis of output noise of FOG, wavelet threshold de-noising theory is applied in FOG's signal processing, and the method is compared with Strong Trace Kalman Filtering optimal estimation method based on ARIMA model.

在分析了光纤陀螺输出噪声的基础上，将小波阈值去噪理论应用到光纤陀螺信号处理中，并与基于ARIMA模型的强跟踪Kalman滤波去噪方法进行了比较。

We fould that most reconstruction algorithm based on wavelets did not consider about the noise. And so, we proposed the denoised reconstruction algorithm based on seperable MRA, in which added regularizion denoised method based on wavelets.

发现大多数小波重建算法都没有对图像的噪声进行处理，基于此，提出了对基于可分离MRA的小波去噪重建算法，融入了基于小波的阀值化去噪算法。

Chapter two was developed the fundamental theorem of speech enhancement, in which the characteristics of speech versus noise, and the model of the speech formation as well, were analyzed. By Combining the conventional evaluating method for speech enhancement system with modern techniques, a new method was proposed, and an experimental system was eventually worked out.

本文以带噪语音为研究对象，开展了带噪语音增强的基础研究工作，从理论和实践上对语音增强的各种算法进行了深入而系统的研究，尝试了在原有谱相减法的基础上引入隐马尔科夫模型、矢量量化及人工神经网络等研究方法及手段并提出了相应的语音增强算法。

This paper discusses the defect of quadratic loss function and studies the models of inverted Normal and inverted Gamma loss function.

本文讨论了二次损失函数模型的局限，在此基础上研究了逆正态、逆伽玛损失函数模型；探讨了质量损失函数与信噪比的关系，提出了基于信噪比的多元质量损失函数模型，克服了单质量属性不能反映实际中多维质量属性的质量损失的弊端，实例证明该方法是可行的。

Breath, muscle contraction of the buttocks; arch body, as far as possible to hold his head, right leg straight towards the ceiling (peg-leg knee in order to avoid muscle tension).

呼气，收缩臀部肌肉；拱起身体，尽量抬起头来，右腿伸直朝向天花板（膝微屈，以避免肌肉紧张）。

The cost of moving grain food products was unchanged from May, but year over year are up 8%.

粮食产品的运输费用与5月份相比没有变化，但却比去年同期高8％。