搜索资源列表
matlabkuozhanbiancheng
- matlab扩展编程——matlab扩展编程完整版，pdf格式，包含语音部分的两章的matlab例程-Matlab programming expansion -- Matlab version of the expansion program integrity, pdf format, part of the speech contains two chapters of Matlab routines
vq
- 说话人识别是语音识别的一种特殊方式，其目的不是识别语音内容，而是识别说话人是谁，即从语音信号中提取个人特征。采用矢量量化（VQ）可避免困难的语音分段问题和时间归整问题，且作为一种数据压缩手段可大大减少系统所需的数据存储量。本文提出了识别特征选取采用复倒谱特征参数和对应用VQ的说话人识别系统改进的一种方法。当用于训练的数据量较小时，复倒谱特征可以得到比较稳定的识别性能。VQ的改进方法避免了说话人识别系统的训练时间与使用时间相差过长从而导致系统的性能明显下降以及若利用自相关函数带来的大量运算。-Sp
9200
- 此系统的开发是实现一个功能较强的、能够提供高质量的图象、语音信号的中枢SERVER，用户可以通过PC的WLAN来访问该服务器，可以对如家庭、办公室、商场、公共会所等提供24小时的实时监控，也可以把图象、语音信号存储在计算机硬盘上。-the development of this system is a more powerful, able to provide high-quality images, Speech signals the central server, users can W
A-Low-Power-Hardware-Architecture-for-SPEECH-RECO
- A Low-Power Hardware Architecture for SPEECH RECOGNITION
SPEECH-ENHANCEMENT-ALGORITHMS-A-BRIEF-REVIEW
- SPEECH ENHANCEMENT ALGORITHMS A BRIEF REVIEW
Speech-endpoint-detection-
- 资料介绍了在matlab平台下进行语音端点检测的方法及其操作流程，端点检测使有效的语音数据得到了提取。-Information on the process of speech endpoint detection under the MATLAB platform and its operation process, the speech endpoint detection data efficiently extracted.
Speech-synthesis
- 代码中介绍了有文本如何转化为语音信号的方法，代码可以调试运行，效果良好-The code and introduces how the text into speech signal, the code can be debugged, good results
SPEECH-RECOGNITION-BY-LD3320
- 一个详细介绍如何应用LD3320实现语音识别的详细文章，自己写的-an essay that can introduce the speech recognition by myself
Speech-Recognition-using-NN
- speech recognition / matlab / -speech recognition / matlab / nn
Speech-Recognition
- Speech Recognition Systems
VISUAL--SPEECH--SYNTHESIS.docx
- vb document for visual speech synthesis
speech-recognition
- 基于MATLAB的语音端点检测短时能量matlab实现短时过零率matlab实现-Speech endpoint detection based on MATLAB short-time energy MATLAB short-time zero crossing ratio of MATLAB
example-of-speech-recognition
- 一个基于带动量项的BP神经网络语音识别的例子-A drive the amount of the BP neural network based speech recognition as an example
ALL-POLE-SPEECH-MODELING-WITH-A-MAXIIMLLY-PULSE-L
- ALL-POLE SPEECH MODELING WITH A MAXIIMLLY PULSE-LIKE RESIDUAL
A-Speech-Analysis-Algorithm.-Model-Reference-Adap
- A Speech Analysis Algorithm Which Eliminates the Influence of Pitch Using the Model Reference Adaptive System
On-Robust-Linear-Prediction-of-Speech
- On Robust Linear Prediction of Speech
Raspberry-pi-speech-Translator
- 在设计物联网系统时,由 Sensor 所感测的数据,经云端运算后,常常将结果由语音方式透过 client 端设备 (手机,浏览器,树莓派),传达给 User Microsoft Azure Marketplace 提供了 Microsoft Translator Api语音转换服务: http://www.wpdang.org/archives/159187.html 使用者可在 client 程序使用 Microsoft Translator Api 所提供的方法将文字转为语音后由喇叭
Keyword-Spotting-Documentation-Speech-Processing.
- Another common KWS method is Acoustic KWS. Using this method, the engine does not attempt to transcribe the entire stream of speech. Like the LVCSR-based method, this method employs the Viterbi search.
Speech-recognition-papers
- 基于小波消噪的毕业论文 很好的参考 查重20 。里面涉及到很多的语音处理。-Based on wavelet de-noising of 20 for graduation thesis very good reference. It involves a lot of speech processing
A-4.8-kbs-high-quality-speech
- 论文：A 4.8 kbs high-quality speech coding using various types of excitation.pdf，讲述一种使用各种激励源的4.8k高质量话音编码算法-A 4.8 kbs high-quality speech coding using various types of excitation.pdf