搜索资源列表
vad
- 双门限端点检测。因为低噪声导致假过零率的产生，进行了算法改进。可以直接调用函数运行，亲测-Dual threshold endpoint detection. Because of the low noise cause false over-produce zero rate, the algorithm was improved. It can directly call the function run, pro-test
vad
- 关于端点检测的几种方法，语音样本是自己录制的，对传统算法做了一些改进，加入了去噪，去噪之后再进行端点检测，均调通 vad0303：自己设置调整门限为一定值 vad0310：根据能量值和过零率设置门限，自适应门限值 vad0310_2：基于比例因子的门限自调整 vad0310.m加入了噪声，端点检测前都噪声进行了处理 entropy.m：基于自适应子带频谱熵的稳健性语音端点检测 可用于语音增强及端点检测 dbdoor.m：双门限算法，用于语音端点检测。可以通过调整门限值，并
Untitled2
- 语音信号是一种非平稳的时变信号，提取的特征参数短时平均过零率-Voice signal is a non-stationary time-varying signal, the extracted characteristic parameter time average zero-crossing rate
Endpoint-detection
- 基于短时能量和过零率的端点检测，里边包括分帧函数，求短时过零率函数-Endpoint detection based on short-term energy and zero-crossing rate
Voice Discern For STM32F
- 于市售 STM32 开发板上实现特定人语音识别处理项目。识别流程是：预滤波、ADC、分帧、端点检测、预加重、加窗、特征提取、特征匹配。端点检测(VAD)采用短时幅度和短时过零率相结合。检测出有效语音后，根据人耳听觉感知特性,计算每帧语音的 Mel 频率倒谱系数(MFCC)。然后采用动态时间弯折(DTW)算法与特征模板相匹配,最终输出识别结果。先用Matlab对上述算法进行仿真，经数次试验求得算法内所需各系数的最优值。而后将算法移植到 STM32 开发板上，移植过程中根据 STM32 上存储空间相
STM32-Speech-Recognition-Master
- 于市售 STM32 开发板上实现特定人语音识别处理项目。识别流程是：预滤波、ADC、分帧、端点检测、预加重、加窗、特征提取、特征匹配。端点检测(VAD)采用短时幅度和短时过零率相结合。检测出有效语音后，根据人耳听觉感知特性,计算每帧语音的 Mel 频率倒谱系数(MFCC)。然后采用动态时间弯折(DTW)算法与特征模板相匹配,最终输出识别结果。先用Matlab对上述算法进行仿真，经数次试验求得算法内所需各系数的最优值。而后将算法移植到 STM32 开发板上，移植过程中根据 STM32 上存储空间相
energyZero
- 读取播放，零能量，现将wav格式的音频文件进行分帧，求能量，过零率-it is easy
pyAudioAnalysis-master
- 实现语音的分割和识别，语音分割通过短时能量和过零率，语音识别通过dtw算法。-audio cut and reconige
shortTimeAnalysis
- 本压缩包是对语音信号的短时分析，包含短时能量、短时过零率、短时自相关以及短时平均幅度差等函数-The compressed package is a short-term analysis of the speech signal, comprising short-time energy, short-term zero-crossing rate, short-term as well as short-time average magnitude of the autocorrelatio
calculmthondetectionand
- 语音信号端点检测仿真,内容涉及短时能量及过零率的计算-Speech signal endpoint detection simulation, the content involves the short-time energy and zero crossing rate calculation
en
- 语音信号的时域和频域处理，包括各种参数，短时能量、短时平均过零率等-The time and frequency domain of the speech signal, including various parameters, short-term energy, short-term average zero-crossing rate, etc.
yuyinfenxi
- 利用自相关或平均幅度差提取基音原理，帧长160，帧移80。求能量E、过零率Z和基音周期pitch；采用自相关法或平均幅度差法求取基音周期，基音周期范围（80~400hz）；画出能量、过零率和基音曲线。(Pitch principle is extracted by means of autocorrelation or mean amplitude difference)
heapenqueue
- 语音信号端点检测仿真,内容涉及短时能量及过零率的计算(Speech signal endpoint detection simulation, the content involves the short-time energy and zero crossing rate calculation)
matlab
- 语音信号的短时分析，主要包括：分帧、短时能量、短时平均幅度、短时过零率、短时自相关函数、短时幅度差、倒谱、复倒谱、lpc系数、lpc谱估计等(The short-time analysis of speech signal mainly includes: frame, short-time energy, short time average amplitude, short-time zero crossing rate, short-time autocorrelation functio
audioFeatureExtraction
- 过零率 (zero-crossing rate,ZCR)是指一个信号的符号变化的比率，例如信号从正数变成负数或反向。 这个特征在语音对比、语音识别和音乐信息检索(music information retrieval)领域得到广泛使用。(Zero-crossing rate (ZCR) refers to the rate at which a signal changes sign, for example, the signal changes from positive to negati
bin
- MATLAB语音信号短时分析，包括自相关，能量谱，过零率等(Short time analysis of MATLAB speech signals, including autocorrelation, energy spectrum, zero crossing rate, etc.)
vad
- 可对一段信号进行分帧加窗，利用过零率和短时能量检测语音端点(It can divide the frame into a window and use the zero crossing rate and short time energy to detect speech endpoints.)
endpoint
- 读取语音文件，预处理，短时能量、过零率分析，进行端点检测(Read voice files, preprocessing, short time energy, zero crossing rate analysis, endpoint detection.)
audio_tezheng
- 语音信号的时域、频域与倒谱域分析。 1.分析一帧清音和浊音的自相关函数和倒谱系数 2.用Matlab画出该段语音的时域波形、短时能量、短时平均幅度、短时过零率、短时过电平率 3.选择一帧无声、清音和浊音的语音，用Matlab画出它们的对数幅度谱(Time domain, frequency domain and cepstrum domain analysis of speech signals. 1. Analyze the autocorrelation function and c
project_V3（注释）
- 可以对所给正弦信号进行采样，并判断过零点且输出频率和正弦信号一样的方波信号。用ePWM模块来确定采样频率，来一次中断采样一次，确保采样率。并对所采样的数据进行有效值计算(The given sinusoidal signal can be sampled and the zero-crossing point can be determined and the square wave signal with the same frequency as the sinusoidal signal