Speech Based Watermarking for Digital Images

在Matlab中的数字图像水印技术中，提出了一种基于盲离散小波变换（DWT）域特征点的图像水印方法。该方法将水印嵌入到由Harris检测器定义的图像特征点中，并通过密钥相关算法从现有特征点生成附加特征

Abstract-Traditional speech information hiding methods have several disadvantages, for example, cons

这个是一个基于LPC的语音合成小project，里面包含了对project介绍的ppt

Single-Channel Speech Separation Based on Deep Clustering with Local Optimization

GMM based classification of speech under stress using physical features

基于词袋模型的文本情感倾向性分析没有考虑句子的句法结构对句子语义的理解,基于依存句法分析的方法试图解决这一问题. 目前基于依存句法分析的方法对影响文本情感的依存关系的选择多根据人为观察,带有随意性.

Speech separation based on signal-noise-dependentdeep neural networks for robust speech recognition

A permutation algorithm based on dynamic time warping in speech frequency-domain blind source separa

End-to-End Deep Learning Framework for Speech Paralinguistics Detection Based on Perception Aware Sp

一篇非常实用的关于用DTW和cross-words refernce模板实现的语音识别文档。