搜索资源列表
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
AnadaptiveKalmanfilterfortheenhancementofspeechsig
- This paper deals with the problem of speech enhancement when a corrupted speech signal with an additive colored noise is the only information available for processing. Kalman filtering is known as an effective speech enhancement technique, in w
RobustadaptiveKalmanfilteringbasedspeechenhancemen
- This paper deals with the problem of speech enhancement when only a corrupted speech signal is available for processing. Kalman filtering is known as an effective speech enhancement technique, in which speech signal is usually modeled as autore
biyelunwen
- 清华大学关于语音端点检测的论文 清华大学关于语音端点检测的论文-Tsinghua University, on Speech Endpoint Detection Tsinghua University dissertation on the voice activity detection paper on Speech Endpoint Detection Tsinghua papers
pcm
- 语音编码方案的选取对移动通信系统的通话质量、信道容量等有重要影响。本文讨论了TD-SCDMA系统中AMR语音编码的自适应机制，同时分析了AMR中代数码本线性预测(ACELP)算法及实现过程。该方案可以在一块TMS320C5510上实现。-The selection of voice coding schemes for mobile communication systems the quality of the call, such as channel capacity have had a
AT89C52ANDISD2560design
- 目前，语音合成、语音识别、语音存储和回放技术的应用越来越广泛，尽管利用一般的单片机测控系统中都有的硬件电路¬ （如A/D、 D/A、存储器等）能完成语音信号的数字化处理，但是功能比较单一、且效果不是很好。本文采用单片机AT89C52与语音芯片ISD2560组成的语音存储系统，实现了语音的分段录取、组合回放，结合LCD液晶显示模块OCMJ2X8，可实现简单的公交报站功能。系统硬件电路简单，调试方便，性价比高，实用性强。 -Currently, speech synthesis, spee
Speechemotionrecognition
- paper for speech emotion recognition
SpeechemotionrecognitionSVM
- paper for speech emotion 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
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
speech-enhancement
- 本文介绍了一种基于自适应滤波算法的语音信号增强处理的方法。文中在扼要介绍了目前常用的语音增强方法的基础上，重点介绍了采用LMS算法的自适应语音增强系统。对三种LMS算法（基本LMS算法,符号误差LMS算法及NLMS算法）进行仔细研究，并用Matlab仿真实现，验证比较了三种算法的语音增强效果。-In this paper, a system of speech enhancement is discussed based on self-adaptive algorithm. On the ba
Speech-Recognition-using-NN-Using-WEKA-Tool
- This good paper on speech recognition using neural networks with WEKA tool-This is good paper on speech recognition using neural networks with WEKA tool
speech-coummunication-
- In this paper we present a robust voice activity detection algorithm which enables further bit rate reduction for practical speech communication systems. -In this paper we present a robust voice activity detection algorithm which e
Homomorphic-Analysis-of-Speech
- 在本文中，我们将提出一种分离语音组成部分的程序进行讨论。该程序是基于对非加性信号的非线性滤波的方法，也被称作广义线性滤波。- In this paper, a procedure for separating the components of speech is proposed and discussed. The procedure is based on an approach to nonlinear filtering of signals which have been n
paper-of-VAD
- 语音端点检测的各种论文，包括MFCC、过零率、短时能量、小波以及谱熵等方法，对编写语音VAD算法有很大的帮助-Speech endpoint detection in a variety of papers, including MFCC, zero-crossing rate, short-term energy, wavelet and spectral entropy method, write voice VAD algorithm of great help
Diphone-Based-Concatenative-Speech-Synthesis
- This paper describes the first Text-to-Speech (TTS) system for the Mongolian language, using the general speech synthesis architecture of Festival. The TTS is based on diphone concatenative synthesis, applying TD-PSOLA technique. The conversion proce
Building-of-a-Speech-Corpus-Optimised-for-Unit-Se
- The paper deals with the process of designing a phonetically and prosodically rich speech corpus for unit selection speech synthesis. The attention is given mainly to the recording and verification stage of the process.
speech-modeling-based-on-HNM.pdf
- this paper presents a speech modeling method that supposes speech to be formed of harmonic and noise part.
estimation-of-speech-harmonic-model.pdf
- this paper presents and compares four time-domain approaches for estimating the parameters of a harmonic speech model.
Automatic-Emotion-Recognition-by-the-Speech-Signa
- This paper is based on emotion recognition of speech signals. Recognizing person s emotional state is an important task.