汉语儿童情感语声合成

情感语声合成技术对于人机交互具有重要的意义。面对儿童情感语声合成所需汉语语声数据资源缺乏以及模型训练时长较长等问题,该文提出利用迁移学习实现汉语儿童情感语声合成的方法。首先基于汉语语声数据库训练深度学习模型实现中文语声端到端合成模型,再使用高质量大样本的中文情感语料库完成情感语声合成模型,最后利用自行采样的小样本汉语儿童情感语料对模型进行迁移学习实现低资源的语声合成。客观实验结果中梅尔倒谱失真指标为4.91,主观听辨实验指标分别为3.61和4.17。通过实验对比表明,该文的方法在情感语声合成技术的应用上具有良好的性能表现,并且优于现有先进的低资源情感语声合成方法。     

语音信号序列的Volterra预测模型

对给定的英语音素、单词和语句进行了采集并完成预处理. 分别应用互信息法和Cao 氏法确定了实际采集的语音信号序列的延迟时间和嵌入维数, 以完成语音序列的相空间重构. 通过计算实际采集的语音信号序列的最大Lyapunov指数, 完成了语音信号的混沌特性识别, 判定其具有混沌特性. 引入Volterra级数, 提出了一种具有显式结构的语音信号非线性预测模型. 为克服最小均方误差算法在Volterra模型系数更新时固有的缺点, 在最小二乘法基础上, 应用基于后验误差假设的可变收敛因子技术, 构建了一种基于Davidon-Fletcher-Powell算法的二阶Volterra 模型(DFPSOVF), 并将其应用于具有混沌特性的语音信号序列预测. 仿真结果表明: DFPSOVF非线性预测模型对于单帧和多帧语音信号均具有更好的预测精度, 优于线性预测模型, 并且能够很好地反映语音序列变化的趋势和规律, 完全可以满足语音预测的要求; 可以根据语音信号序列的嵌入维数选取预测模型的记忆长度. 所提出模型可以为语音信号重构和压缩编码开辟一条新途径, 以改善语音信号处理方法的复杂度和处理效果.     

结合隐藏技术的新颖语音检索算法

采用一种新颖的结合信息隐藏技术的语音检索算法，该算法将保密语音和伪语音分割成多段，利用经典的LSB算法分别隐藏到不同的音频，并存储在磁盘空间中．提取语音码流时，利用小波变换第一级细节分量系数能量的大小找到相应的载体音频，提取其中的语音码流，并建立语音库．利用特定人语音检索技术，检出相应的语音码流，合并语音码流得到真正的保密语音．研究表明：新算法的查准率和查全率可以达到很高的水平，为信息隐藏技术的发展开辟了一条新的研究道路，同样扩大了语音检索技术的应用范围。     

基于MMSE先验信噪比估计的语音增强

针对传统最小均方误差（MMSE）沿爵增强方法无法准确处理快速语音的变化问题，提出了一种堆于MMSE估计先验信噪比的语音增强方法，利用该笔法估计每帧语音俯号的每一个频率分量上的平滑系数αn,k。进行平均反馈估计，从而得到更加接近于真实情况的先验信噪比，进而使用MMSE方法进行语音的增强，提高了对于快速变化语肯的增强效果，实验结果农明，本方法比传统MMSE语青增强方法在增强性能上提高了近2dB。     

Multimodal Interfaces for Cell Phones and Mobile Technology

By modeling users' natural spoken and multimodal communication patterns, more powerful and highly reliable interfaces can be designed that support emerging mobile technology. In this paper, we highlight three different examples of research that is advancing state-of-the-art mobile technology. The first is the development of fusion-based multimodal systems, such as ones that combine speech and pen or touch input, which are substantially improving the robustness and stability of system recognition. The second is modeling of multimodal communication patterns to establish open-microphone engagement techniques that work in challenging multi-person mobile settings. The third is new approaches to adaptive processing, which are able to transparently guide user input to match system processing capabilities. All three research directions are contributing to the design of more reliable, usable, and commercially promising mobile systems of the future.     

利用倒谱方法实现气声发育的重建

本文介绍了一种利用复倒谱来实现气声发音重建的方法。首先分析了气声发音的语音特征；进而在复倒谱序列中加入基频特征使其恢复到正常的语音。对元音［a］以及实际语音段进行了处理，均有较好的效果。     

人类对超声的听觉感知及应用前景

本文对人类通过骨传导所产生的超声听觉感知，就以下四方面进行介绍：１．感知的方法、频率和强度范围；２．感知机理；３．可能的应用；４．值得研究的问题。     

Consistency analysis of the spectrum and prosody within a syllable for Mandarin speech

This work presents a study of Mandarin speech focusing on consistency analysis of the spectrum and prosody within syllables. Identified as a result of inspection of the human pronunciation process, this consistency can be interpreted as a high correlation between the warping curves of the spectrum and the prosody intra a syllable. The consistency analysis consisted of three steps. First, the hidden Markov model algorithm was used to decode the hidden Markov model‐state sequences within a syllable, while at the same time dividing them into three segments. Second, based on a designated syllable, the vector quantization (VQ) with the Linde–Buzo–Gray algorithm was employed to train the VQ codebooks of the prosodic vector of each segment. Third, the prosodic vector of each segment was encoded as an index using the VQ codebooks, and then, to analyze the consistency, the probability of each possible path was evaluated as a prerequisite. Finally, two syllables were used as examples to verify the consistency property found in the experiments. It is demonstrated experimentally that there is definitely consistency in the case where the syllable is located in exactly the same word. These results offer a research direction in that the warping process between the spectrum and the prosody intra a syllable must be considered in text‐to‐speech systems to improve the synthesized speech quality. Copyright © 2013 John Wiley & Sons, Ltd.     

Study of the formant and duration in Chinese whispered vowel speech

Study on the acoustical characteristic is important to speech and speaker recognition in Chinese whispered speech. In this paper, the characteristics of whispered speech are introduced and the acoustical characteristics in Chinese whispered speech are discussed. There is no fundamental frequency in the whispered speech, so other characteristics such as the duration and frequency of formant are extracted and analyzed. From experiments with six simple Chinese whispered vowels, it is proved that the duration and the frequency of formant can be used as the main acoustical characteristics in the Chinese whispered recognition.     

定点脉冲线性预测编码方法研究*

在多脉冲线性预测编码的基础上,本文提出了位置无关脉冲搜索算法。该算法不需要搜索脉冲位置,而是根据给定的脉冲位置一次性解出脉冲幅度矢量。这就保证了得到的脉冲组合在最小二乘意义下是最优的,为改进合成语音质量提供了理论基础。进而在激励脉冲与位置无关的理论基础上,提出了定点脉冲线性预测编码方法。对所提出的算法在MATLAB下进行了仿真,仿真结果发现位置无关脉冲搜索算法得到的合成语音质量优于序贯法,编码时间也要比序贯法短。定点脉冲线性预测编码方法可以在2.7 kbps的编码速率下获得与G.729相近的合成语音。