此程序为自相关法进行基音检测的程序，主要应用于语音识别。...

N best hypothesis document N best hypothesis as used H-N best hypothesis document N best hypothesis as used HMM

自编的语音语谱图程序，适用于语音信号处理以及语音增强处理，-self Speech Spectrogram procedures applicable to the speech signal processing and speech enhancement.

The Yin algorithm was developed by Alain de Cheveigné of IRCAM-CNRS and Hideki Kawahara of Wakayama University. It allows for real-time continuous (for each sample) fundamental frequency estimation. It features a very low error rate and few tuning parameters. This implementation is a C++ template, with EMM support for faster processing. Developped in Visual C++ 6.0, but should compile with other compilers.-The Yin algorithm was developed by Alain de Cheveigné of IRCAM-CNRS and Hideki Kawahara of Wakayama University. It allows for real-time continuous (for each sample) fundamental frequency estimation. It features a very low error rate and few tuning parameters. This implementation is a C++ template, with EMM support for faster processing. Developped in Visual C++ 6.0, but should compile with other compilers.

为了实现高速语音特征参数的提取，在分析了美尔频率倒谱特征参数提取算法的基础上，提出了算法的硬件 设计方案，介绍了各模块的设计原理。该方案增加了语音激活检测功能，可对语音信号中的噪音帧进行检测，提高了特征参 数的可靠性。-In order to achieve high-speed voice characteristic parameter extraction, in the analysis of Mel frequency cepstral feature extraction algorithm is proposed based on the algorithm the hardware Design, describes the design principles of each module. The program increased the Voice Activity Detection feature, which allows voice signals to detect the noise frame to improve the characteristic parameters The number of reliability.

自编的几个关于数字信号基本运算的程序，由此可以大大扩展信号运算的自由性与简洁性。-wrote several digital signal on the basic operations procedures, It can be greatly expanded signal operation and the freedom of simplicity.

一款安卓版的语音小助手，调用了讯飞的API，实现了用语音指令打电话、发短信、查看日历、搜索、打开应用等数十项功能，类似于APPLE的SIRI，用Android studio开发。

几种语音增强关于mmse算法，维纳滤波，掩蔽增强-err

构造一组被噪声污染的方波或三角波数据，试选取适当的FIR滤波器结构和参数，分别应用LMS,DFT/LMS和DCT/LMS算法来实现自适应滤波器，对改组数据进行滤波，并分析仿真结果。-Construction Group was one of the Noise Pollution square or triangular wave data, Examination choose appropriate FIR filter structure and parameters, application LMS, DFT/LMS and DCT/LMS algorithm to achieve adaptive filter, the reorganization data filtering, and analysis of simulation results.

英语学习(tts和access的应用)-English learning (TTS and access to the application)

线性量化。读取WAV文件，用不同的比特数量化，抽样频率在8khz-Linear quantization. Read WAV files, with different number of bits, the sampling frequency of 8kHz