Wavelet De-noising of Speech Using Singular Spectrum Analysis for Decomposition Level Selection

The problem of speech enhancement using threshold de-noising in wavelet domain was considered.The appropriate decomposition level is another key factor pertinent to de-noising performance.This paper proposed a new wavelet-based de-noising scheme that can improve the enhancement performance significantly in the presence of additive white Gaussian noise.The proposed algorithm can adaptively select the optimal decomposition level of wavelet transformation according to the characteristics of noisy speech.The experimental results demonstrate that this proposed algorithm outperforms the classical wavelet-based de-noising method and effectively improves the practicability of this kind of techniques.     

噪声背景下语音识别中的端点检测

整个实验系统主要研究的是语音识别中在噪声背景下的端点检测.在实际环境中,加性背景噪声对语音识别的影响非常大,在信噪比小的情况下,无法进行端点检测.在此研究过程中,首先进行加性噪声模型的建立,而后通过滤波对带噪语音信号进行预处理,这里采用维纳滤波和自适应LMS滤波进行滤波.在进行语音信号的预处理后,使用VAD算法进行端点检测.建立整个实验系统后,通过试验比较维纳滤波器和自适应LMS滤波器的优劣,找出最佳方案.     

ENDPOINT DETECTOR OF NOISY SPEECH SIGNAL USING A RECURRENT NEURAL NETWORK

ＩｎｔｒｏｄｕｃｔｉｏｎＥｎｄｐｏｉｎｔｄｅｔｅｃｔｉｏｎｏｆｓｐｅｅｃｈｓｉｇｎａｌｉｓｉｍｐｏｒｔａｎｔｉｎｍａｎｙａｒｅａｓｏｆｓｐｅｅｃｈｐｒｏｃｅｓｓｉｎｇｔｅｃｈｎｏｌｏｇｙ,ｓｕｃｈａｓｓｐｅｅｃｈｅｎｈａｎｃｅｍｅｎｔ,ｓｐｅｅｃｈｒ...     

Fuzzy C-Means Clustering Based Phonetic Tied-Mixture HMM in Speech Recognition

A fuzzy clustering analysis based phonetic tied-mixture HMM (FPTM) was presented to decrease parameter size and improve robustness of parameter training. FPTM was synthesized from state-tied HMMs by a modified fuzzy C-means clustering algorithm. Each Gaussian codebook of FPTM was built from Gaussian components within the same root node in phonetic decision tree. The experimental results on large vocabulary Mandarin speech recognition show that compared with conventional phonetic tied-mixture HMM and state-tied HMM with approximately the same number of Gaussian mixtures, FPTM achieves word error rate reductions by 4.84% and 13.02% respectively. Combining the two schemes of mixing weights pruning and Gaussian centers fuzzy merging, a significantly parameter size reduction was achieved with little impact on recognition accuracy.     

基于言语行为理论的法庭语言探究

文中从言语行为的角度卅发对法庭中法官、律师的语言进行了分析,总结出法庭言语行为的几个构成性原则,并对这几个主要的构成性规则进行了阐述。     

海上固定平台PA/GA系统设计

论文介绍了海上固定平台PA/GA系统的设计原则及方法,并结合海上工程项目,分析并阐述了该系统功能、技术要求及关键参数计算和选取;对实现海洋固定平台公共广播和报警系统的优化设计,具有重要的指导意义和参考价值。     

A Magic Book Out of Magic Language

Harry Potter booksare great successes, enjoyed by readers' all over the world. Harry Potter and the Philosopher's Stone is the debut of the sequel books, which is about magic and the magical life a little boy-Harry Potter, a born wizard. People are always curious and eager to discover the secrets of magic, to meet the end of the heroes' fates, but not many of them pay attention to the book's language. Actually, I think it is the skillful use and application of language that make the book outstanding. Therefore, this paper mainly discussesthe language features of Harry Potter and Philosopher's Stone from these four as-pects: speech sounds, choice of vocabulary, sentence structures and figures of speech, aiming at exploring and revealing the charmsof the magic book.     

嵌入式VDR系统语音处理卡的研制

语音处理卡是船舶航行数据记录仪（Voyage Data Recorder，简称VDR）中针对语音信号的一个子系统。研制时，在硬件方面，对基于AC48304C-C核心芯片的系统结构及其电路原理图进行了设计；软件方面，采用了面向对象的模块化设计，在VxWorks操作系统Tomado开发环境下运用C＋＋语言编制了语音卡的功能程序。它实现了多路模拟语音的采集和压缩。     

基于DSP的话音系统设计及语音处理算法实现

介绍了一种基于802．3以太网协议传输话音和数据的局域通信系统的设计。该通信系统采用两块TI公司的54、系列芯片构成主从连接方式，作为通信系统信号处理与控制平台，通过系统功能要求可实现重配置以及相应应用软竺的可选择下载执行。为保证话音与数据通信的可靠性与实时性，由5416负责话音的采集与处理，实现了包括语音检测、语音编解码、回声消除、自适应降噪等语音处理算法。系统工作情况表明，达到了设计要求。     

基于Web的英语自助学习系统设计

分析了基于Web的英语自助学习系统的工作原理,选择Microsoft Speech SDK5.1并在其基础之上封装WebVoiceCtl作为构建系统的核心技术。调用Text To Speech Engine完成文本语音转换,实现基于Web的英语听力测试。此外,通过Web-VoiceCtl控件调用Speech Recognition Engine完成语音识别,实现基于Web的英语口语测试。最后,在ASP.NET环境下实现英语自助学习软件系统,该软件可提供基于Web的英语听、说、写等技能训练。