资源列表
11
- 为提高语音端点检测系统在低信噪(0 dB 以下) 下 检测的准确率, 提出了一种基于谱熵的端点检测算法。将每 帧信号分为16 个子带, 选取频谱分布在250～ 3. 5 kHz 并且 能量不超过该帧总能量90 的子带, 计算经过语音增强后的 子带能量以及各子带信噪比, 根据各子带信噪比的不同调整 其在整个谱熵计算过程中的权重, 然后平滑谱熵, 以最终的 谱熵作为端点检测的依据-To improve endpoint detection system in the low
hmm
- hidden markov model toolkit
2D-PCA
- FACE RECOGNITION USING K-L TRANSFORM on ORL face database
2006011093
- 基本语音识别与合成的算法，如各个音的声音频率的确定等等，并且可以做变化和包络后实现声音效果的改变-Basic speech recognition and synthesis algorithms, such as the sound of each sound to determine the frequency, etc., and can do to achieve change and enveloping sound effects after the change
Speech-Control
- 介绍以VC6.0和Microsoft Speech SDK5.1为开发工具,开发语音交互界面应用程序，实现语音控制模拟机械臂完成简单动作和关闭程序的完整过程。-introduces the VC6.0 and Microsoft Speech SDK5.1 for the development of tools to develop voice interface applications, voice controlled robotic arm simulation program to
Matlab
- 语音端点检测基于短时能量的Matlab程序-Speech endpoint detection based on short-time energy of the Matlab program
Voice-integer-IIR-filter-C-program
- 语音的IIR滤波程序，可以实现对语音信号的IIR整型滤波-Voice of the IIR filter program, you can achieve integer IIR filtering of speech signals
speechenhance
- 基于谱减法的语音增强，重点在噪声的估计，效果还可以-Speech enhancement based on spectral subtraction, focusing on the estimated noise, the effect can also be
tts_speechrecogniton
- 用户使用本软件之前请先配置sapi文件，这是一个可以运行的TTS语音朗读软件，使用VC 6.0开发。-Users before using this software please first configuration sapi files, this is a can run the TTS voice reading software, using VC 6.0 development.
Microsoft-Speech-SDK
- 微软公司的语音开发资料，实现了语音合成和识别的功能-Microsoft' s speech development information, realize the function of speech synthesis and recognition
speech
- 语音识别源码，可以实现用户同机器之间的语音交互，效果不错-Speech recognition source code, the user can interact with the machine between the voice and good results
TTS_SR-speech-recognition
- 应用程序通过ISpVoice 组件对象接口（Component Object Model Interface）来控制Text-To-Speech (TTS)。及SR引擎。-Application through ISpVoice Component Object Interface Component Object Model (with) To control To sites- bring (TTS).- And SR engine.