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。     

An Improvement to Conformer-Based Model for High-Accuracy Speech Feature Extraction and Learning

Owing to the loss of effective information and incomplete feature extraction caused by the convolution and pooling operations in a convolution subsampling network, the accuracy and speed of current speech processing architectures based on the conformer model are influenced because the shallow features of speech signals are not completely extracted. To solve these problems, in this study, we researched a method that used a capsule network to improve the accuracy of feature extraction in a conformer-based model, and then, we proposed a new end-to-end model architecture for speech recognition. First, to improve the accuracy of speech feature extraction, a capsule network with a dynamic routing mechanism was introduced into the conformer model; thus, the structural information in speech was preserved, and it was input to the conformer blocks via sequestered vectors; the learning ability of the conformed-based model was significantly enhanced using dynamic weight updating. Second, a residual network was added to the capsule blocks, thus, the mapping ability of our model was improved and the training difficulty was reduced. Furthermore, the bi-transformer model was adopted in the decoding network to promote the consistency of the hypotheses in different directions through bidirectional modeling. Finally, the effectiveness and robustness of the proposed model were verified against different types of recognition models by performing multiple sets of experiments. The experimental results demonstrated that our speech recognition model achieved a lower word error rate without a language model because of the higher accuracy of speech feature extraction and learning using our model architecture with a capsule network. Furthermore, our model architecture benefited from the advantage of the capsule network and the conformer encoder, and also has potential for other speech-related applications.     

语音增强技术在低速语音编码中的应用

在语音编码的应用环境中,特别是在军事应用中,强噪声环境下声码器性能的改进是一个亟待解决的问题。在研究语音增强技术的基础上,将语音增强技术于低速语音编码,有效地改善了低速语音编码算法的抗背景噪声的性能。并利用所构建的语音质量客观评价平台,对语音增强低速编码算法的抗背景噪声性能进行了客观评估与分析。     

Multi-Level Error Detection and Concealment Algorithm to Improve Speech Quality in GSM Full Rate Speech Codecs

Digital mobile telecommunication systems, such as the global system for mobile (GSM) system, want to further improve speech communication quality without changing the channel encoders and decoders. Speech quality is most affected by residual bit errors in received speech frames. Conventional methods use binary decision strategies for error detection and concealment in frames. This paper presents a multi-level error detection and concealment algorithm for GSM full rate speech codec systems. The algorithm use...     

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。     

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。     

Reliability of Speaking and Maximum Voice Range Measures in Screening for Dysphonia

Speech range profile (SRP) is a graphical display of frequency-intensity occurring interactions during functional speech activity. Few studies have suggested the potential clinical applications of SRP. However, these studies are limited to qualitative case comparisons and vocally healthy participants. The present study aimed to examine the effects of voice disorders on speaking and maximum voice ranges in a group of vocally untrained women. It also aimed to examine whether voice limit measures derived from SRP were as sensitive as those derived from voice range profile (VRP) in distinguishing dysphonic from healthy voices. Ninety dysphonic women with laryngeal pathologies and 35 women with normal voices, who served as controls, participated in this study. Each subject recorded a VRP for her physiological vocal limits. In addition, each subject read aloud the "North Wind and the Sun" passage to record SRP. All the recordings were captured and analyzed by Soundswell's computerized real-time phonetogram Phog 1.0 (Hitech Development AB, T?by, Sweden). The SRPs and the VRPs were compared between the two groups of subjects. Univariate analysis results demonstrated that individual SRP measures were less sensitive than the corresponding VRP measures in discriminating dysphonic from normal voices. However, stepwise logistic regression analyses revealed that the combination of only two SRP measures was almost as effective as a combination of three VRP measures in predicting the presence of dysphonia (overall prediction accuracy: 93.6% for SRP vs 96.0% for VRP). These results suggest that in a busy clinic where quick voice screening results are desirable, SRP can be an acceptable alternate procedure to VRP.     

基于SVM的置信度综合方法在语音识别中的应用

讨论了语音识别中使用支持向量机(support vector machines,SVM)对音子级置信度进行综合的方法. 音子级置信度得分采用传统的方法计算而得,并使用SVM对音子级置信度进行综合得到词级的置信度得分. 在说话人无关的汉语孤立词识别实验中,使用作者方法比使用传统方法获得的系统等错误率rEER(equal error rates,EER)有明显降低,可以从基线系统的28.14%降低到23.71%,而系统的复杂度仅有小幅度的上升.     

用于统计语音合成的大尺度压缩HMM的方法

统计语音合成使用隐Markov模型(HMM)作为声学特征的统计模型。提出了一种利用声学模型空间距离进行HMM的大尺度压缩的量化方法,通过对矢量量化码本进行的优选迭代步骤,减小压缩后的声道谱模型与原模型之间的声学距离,使通过量化模型合成的语音更加接近未量化模型。主观和客观测试结果显示:使用该方法进行声道谱模型的压缩,在压缩至原模型大小的0.06左右时,仍有约90%的评价得分认为合成语音的质量没有明显下降。     

基于听觉场景分析的近讲语音增强算法

针对近讲场景,提出一种双麦克近讲语音增强算法。该算法基于耳间延时差(ITD)、耳间强度差(IID)特征来区分目标语音,利用声学掩蔽效应,实现目标语音对背景噪声的分离降噪。与传统的单麦克增强方法相比,该算法可消除多种类型噪声且对语音造成的损伤较小。实验表明:该算法能将8～33dB的白噪声、音乐噪声、广播噪声3种噪声类型的带噪语音的信噪比提高到36dB以上,同时保持较高的目标语音可懂度。对于冲击噪声的带噪语音也具有较好的降噪效果。