搜索资源列表
yuyinshibiedsp
- 用DSP实现的一个简单的语音识别系统,只要实现单个词的识别即可,采样率8k,帧长30ms,帧移10ms,系统采样后分帧--端点检测,将检测到的原始语音信号保存下来,基本上一个字在30帧左右,然后提取每帧的LPC参数--将LPC参数转换为LPC倒谱系数,然后利用DTW方法和模板比较.-a brief speech recognition system, as long as the realization of a single word can be identified. 8 k sampli
phasevocoder
- 基於相位平移的語音編碼,可提供語音升調以及降調的功能-Based on the phase shift of the speech coding
SIFT_ALGORITHM_FLOW
- shift algorithm in speech
phase-shift--phase-shift-algorithm
- 能够实现MATLAB下相位偏移算法，里面自带一些音频-It is able to achieve a phase shift algorithm in MATLAB, which comes with some audio
OLA
- 编写一Matlab函数，用30ms三角窗和15ms帧移计算语音信号的STFT。并用OLA法重建原始信号。设计一种基于OLA的综合方法，以通过重复每帧对语音信号以因子2进行时域扩展。-Write a Matlab function, STFT and 30ms triangular window and 15ms frame-shift calculation of the speech signal. And the OLA method to reconstruct the original
duanshinengl
- 读取语音信号，计算不同帧数和帧移的短时能量-Read the speech signal, short-term energy to calculate different frames and frame shift
4.8k_CELP
- 语音CELP压缩解压源代码（C语音)- Pronunciation CELP compression decompression source code (C pronunciation) - * 4800 bps CELP Characteristics * * Spectrum Pitch Code Book * ------------- ---------------
wavenergy
- 画出时间波形，画出短时能量图，给出海宁窗，给出帧长和帧移-Time waveform draw, draw short-term energy diagram given Hanning window given frame size and frame shift
Sound-Effect-board
- 这份报告概述了项目修改语音信号与各种不同的效果。实现的效果是一个呼应,相移和残余阈值剪裁。的分析过程和技术参与实施这些技术也提供了一个洞察整个项目选择背后的原因。这份报告将细分一个语音信号的分解步骤,将段到频域,估计谱包络,操纵信号以不同的方式,然后回到回放的时间域。附录中提供一份项目以及示例输出结果。还提到可能的扩展项目,可能会增强其功能和团队的建议进行这些增强功能。-This report outlines a project to modify a speech signal with v
spetro.m
- 语音信号的语谱图生成函数，function [ ] = spetro(Winsiz, Shift, Base, Mode, Gray)，5个参数分别为帧长、帧移、取值门限（一般设为0）、彩色模式、灰度模式-This is a matlab function for creating speech spectrogram.
MFSK_mod
- Multiple frequency-shift keying (MFSK) is a variation of frequency-shift keying (FSK) that uses more than two frequencies. MFSK is a form of M-ary orthogonal modulation, where each symbol consists of one element an alphabet of orthogonal waveforms. M
提取语音信号基频
- 用自相关函数提取语音信号基频，提取音频文件的基频等高线(Use the autocorrelation function on segments of the signal (windowsize: 100ms) and compute the fundamental frequency. Use a max_time_lag of 100ms in the autocorrelation function and a window shift of 25ms. Create a fundame