搜索资源列表
http___www.speech.sri.com_cgi-bin_run-distill_pape
- Accent issues in large vocabulary continuous speech recognition-Accent issues in large vocabulary continu ous speech recognition
HTK-speechRecognition.rar
- 应用HTK建立的语音识别系统,PPT文档,Application of HTK speech recognition system established, PPT document
TIMIT-speech-database
- TIMIT语音数据库,希望给语音研究者提供帮助。-TIMIT speech database, I want to give help to the researchers of voice .
pre-emphasissub-framewindowed matlab编写的关于语音信号预加重
- matlab编写的关于语音信号预加重,分帧加窗的程序。-matlab, prepared by the speech signal pre-emphasis, sub-frame windowed program.
Applied.Speech.and.Audio.Processing.With.MATLAB.E
- Applied Speech and Audio Processing With MATLAB Examples
ALGORITHM
- A SOFT MODEL-ORDER SUBSPACE BASED SPEECH ENHANCEMENT ALGORITHM
speech_recog
- Speech recognition document with C++ codes-Speech recognition document with C++ codes...
voicebox
- this is speech recognition file
wavelettransform
- 基于小波变换的语音增强的语音去噪的MATLAB源程序-Wavelet-Based Speech Enhancement Speech Denoising MATLAB source code
abstract
- abstract on speech recognition robot
Speech
- This is a project report on building a speech recognition robot using HM2007 and Atmel AVR AtMega16 microcontroller. The HM2007 is used to store voice commands and template matching.
fullRreport
- SPEECH RECOGNITION USING DSP full report
hanyuyunlvjiance
- 介绍了汉语口语中韵律边界检测和基于韵律信息的对话行为分类的研究,这个研究对于语音识别中词类的分类和提高准确率具有非常重要的意义-Spoken Chinese Prosodic Boundary Detection and rhythm-based classification of information, dialogue and behavior research, this study parts of speech for speech recognition in the classi
12
- Hidden Markov Modelsand its Application in Automatic Speech Recognition
lunwen
- 本文简要介绍了语音信号采集与分析的发展史以及语音信号的特征、采集与分析方法,并通过PC机录制自己的一段声音,运用Matlab进行仿真分析,最后加入噪声进行滤波处理,比较滤波前后的变化。-This paper introduces the voice signal acquisition and analysis of the history and characteristics of speech signals, sampling and analysis methods, and thro
HMM
- HMM语音识别,文本相关或文本无关均使用的说话人模型-HMM speech recognition, text-related or text-independent speaker model are used
modelbasedonspectrumprediction
- 文章展示了基于高斯混合模型的语音频谱预测方法。频谱预测可能在传包过程中预防丢包这方面起到大作用。期望最大化算法用两倍或三倍的连续语音因素来测试模型。模型被用来设计第一,儿等指令预测量。预测表用频谱分配状态来估计并和一个简单的参考模型对比。最好的预测表得到一个平均频率扭曲值是0.46dB小于参考模型-This paper presents methods for speech spectrum prediction based on Gaussian mixture models. Spec
extraction
- We propose methods to track natural variations in the characteristics of the vocal-tract system from speech signals. We are especially interested in the cases where these characteristics vary over time, as happens in dynamic sounds such as co
speech
- 微软speech sdk实现汉字读取显示功能-Microsoft speech sdk to read Chinese characters display to achieve
Evaluation-of-Speech-Synthesis
- Evaluation of Speech Synthesis