语音信号处理-赵力 PDF

　提出了一种新的连续型隐马尔可夫模型(HMM ) 的概率密度函数, 并导出了一系列的参 数寻优迭代公式,(A new Continuous Hidden Markov Model (HMM) of the probability density function, and derived a series of parameters optimization iteration formula,)

用于说话人识别（声纹识别）中训练过程和识别过程的高斯混合模型程序(GMM model for the training process or test process of speaker identification)

本系统是基于矢量量化技术的说话人识别系统。可根据语音库以及实时录音识别且具有图形用户界面。压缩包内含有源码、语音信息库音频及演示视频等。(The system is based on vector quantization speaker recognition system. Identifiable and has a graphical user interface based on speech and real-time recording. Within the compressed package contains the source code, voice information and presentation of audio and video.)

psola算法的设计与实现，经过调试已经可以运行(psola Algorithm Design and Implementation, after debugging has to run)

手机端蓝牙连接设备（以小车为例），通过按键、本地语音识别（pocketsphinx）和重感控制设备，蓝牙连接地址在BluetoothTools中修改，本地需要配置NDK环境才能编译。(Bluetooth mobile client devices (for example in the car), buttons, local speech recognition (pocketsphinx) and heavy sense of control devices, Bluetooth connectivity address BluetoothTools modify the local environment can be configured to compile NDK.)

计算声音信号的总声压级，1/3/倍频程声压级，总响度，特性响度，尖锐度(Calculation of the total sound pressure level of the voice signal, 1/3/octave sound pressure level, the total loudness, loudness characteristics, acute severe)

观测实时模拟信号（语音）的频谱 用音频设备采集一段语音，将语音存为.wav格式。对wav文件作分段傅里叶变换分析。语音是分音节的，应把它分段分析，而且实际运用中的数字信号处理的FFT的点数是有限的，一般只能达到千点。用傅里叶反变换IFFT，从频域恢复信号。画出频谱图和语音波形图。 (Observing real-time analog signal (voice) of the spectrum collected with the audio devices section of voice, voice saved as. Wav format. Wav file of the sub-Fourier transform analysis to make. Speech is divided into syllables, it should be sub-analysis, and practical application of digital signal processing of the FFT points is limited, generally only reach 1000 points. Fourier inverse transform IFFT, to restore the signal from the frequency domain. Draw the spectrum map and voice waveform.)

线性预测倒谱系数（Linear Prediction Cepstrum Coefficient,LPCC）是线性预测系数（Linear Prediction Coefficient,LPC）在倒谱域中的表示。该特征是基于语音信号为自回归信号的值设，利用线性预测分析获得倒谱系数。(Linear Prediction Cepstrum Coefficient)

EVC 基于CE的TTS源码，需安装语音库(TTS resource code based on wince)

memcached资源demo(已调试通过)(Memcached Resource demo (Debug passed))