基于会议系统混音算法的研究与应用

在多媒体视频会议系统中,语音处理是关键环节,而解决多路混音后的溢出噪声问题是语音处理的核心。现有的混音算法存在音量突变的问题,通过对其分析,找出了最主要的原因。在此基础上,提出了一种改进的算法——自对齐减谱法,经仿真结果表明:该算法消除噪声效果更明显,可用于多媒体视频会议系统中。     

物联网中音频事件检测方法的研究

Recently, the Internet of Things (IoT) has attracted more and more attention. Multimedia sensor network plays an important role in the IoT, and audio event detection in the multimedia sensor networks is one of the most important applications for the Internet of Things. In practice, it is hard to get enough real-world samples to generate the classifiers for some special audio events (e.g., car-crashing in the smart traffic system). In this paper, we introduce a TrAdaBoost-based method to solve the above problem. By using the proposed approach, we can train a strong classifier by using only a tiny amount of real-world data and a large number of more easily colle cted samples (e.g., collected from TV programs), even when the real-world data is not sufficient to train a model alone. We deploy this approach in a smart traffic system to evaluate its performance, and the experiment evaluations demonstrate that our method can achieve satisfying results.     

一种新的基于分类的音频流分割方法

很多传统的音频流分割方法都是基于小尺度音频分类的,它们普遍存在虚假分割点过多的缺点,严重影响了实际应用的效果.我们的研究表明,大尺度音频片段的分类正确率明显高于小尺度音频片段的分类正确率.基于这个事实和减少虚假分割点的目的,我们提出了一种新的基于分类的音频流分割方法.首先,采用基于大尺度分类的分割方法对音频流进行粗分割,然后采用基于小尺度分类的细分割步骤在边界区域中进一步精确定位分割点.理论分析和实验结果均表明,当处理类别变换频率较低的音频流时,这种分割方法在保持真实分割点检测率的同时能够大幅降低虚假分割率.     

传感器网络中基于分层架构的音频场景分析方法

A hierarchical method for scene analysis in audio sensor networks is proposed. This method consists of two stages: element detection stage and audio scene analysis stage. In the former stage, the basic audio elements are modeled by the HMM models and trained by enough samples off-line, and we adaptively add or remove basic element from the targeted element pool according to the time, place and other environment parameters. In the latter stage, a data fusion algorithm is used to combine the sensory information of the same area, and then, a rule-based method is employed to analyze the audio scene based on the fused data. We conduct some experiments to evaluate the performance of the proposed method that about 70% audio scenes can be detected correctly by this method. The experiment evaluations demonstrate that our method can achieve satisfactory results.     

Multi‐channel Audio Service in a Terrestrial‐DMB System Using VSLI‐Based Spatial Audio Coding

Spatial audio coding (SAC) is an extremely high compact representation of encoded multi‐channel audio material. This paper suggests a multi‐channel audio service in the terrestrial digital multimedia broadcasting (T‐DMB) system using a novel SAC tool, which is called a virtual source location information (VSLI)‐based SAC tool. Intensive experiments are presented to evaluate the validity of the proposed VSLI‐based SAC tool, and prototypical systems are also presented to demonstrate the reliability of the proposed multi‐channel T‐DMB system in real applications.     

基于LDPC码的数字音频水印算法研究

论文提出了一种基于低密度奇偶校验(LDPC)码的音频水印算法,对水印进行编码预处理后,采用时域去直流的方法并动态改变水印幅度嵌入水印,其中利用了人耳听觉系统的感知特性,把水印加在人耳感知极限下方。通过仿真实验结果表明,该算法具有较强的鲁棒性和不可感知性,而且在水印检测时不需要原始音频信号。     

AAC:21世纪音频编码的主流

数字音频编码技术无论对多媒体通信、多媒体广播、消费类电子都有其重要性。首先简要地回顾了数字音频编码技术的发展过程,然后介绍了包括MPEG音频,MP3,AC-3,ATRAC,PAC在内的8种现行商用数字音频编码系统,并作了特征比较,作为重点、详细地叙述了MPEG-2AAC的算法和特点。介绍了ITU-R有关高质量音频编码主观评价的方法,给出了AAC,PAC,MP3,AC-3音质评分表,评分显示在相同低数码率时AAC具有最好的音质,达到了ITU-R的有关规定。最后简要介绍了AAC的实现。     

基于凝聚信息瓶颈的音频事件聚类方法

为了进一步提高音频事件聚类算法性能,本文基于凝聚信息瓶颈理论提出一种音频事件聚类方法.首先,论述信息瓶颈原理及其推导过程;然后,详细论述一种基于凝聚信息瓶颈的音频事件聚类方法,包括源变量、相关变量和目标变量的定义,聚类的具体步骤,算法主要计算量分析等.采用取自两个数据库的音频事件样本进行测试,实验结果表明：与目前文献报道的方法相比,本文方法在多种实验条件下都获得了更高的K值（平均类纯度和平均音频纯度的几何平均值）,而且运算速度更快.     

篮球比赛视频节目中短管哨声检测方法

提出了一种检测篮球比赛视频中重要音频关键词（短管哨声）的方法。通过分析短管哨声的频谱分布特性提出一种二级检测方法：首先提取特定子带能量峰指数特征,并采用门限决策方法获得关键词候选集;第二级再结合梅尔频率倒谱系数和支持向量机得到最终的关键词检测结果。选取时长为1378s的NBA篮球比赛音频片段作为测试序列．验证了本方法具有正确率和检出率分别为95．45％和91.3％的性能。