基于多核学习支持向量机的音乐流派分类

针对不同特征向量下选择最优核函数的学习方法问题,将多核学习支持向量机(MK-SVM)应用于音乐流派自动分类中,提出了将最优核函数进行加权组合构成合成核函数进行流派分类的方法。多核分类学习能够针对不同的声学特征采用不同的最优核函数,并通过学习得到各个核函数在分类中的权重,从而明确各声学特征在流派分类中的权重,为音乐流派分类中特征向量的分析和选择提供了一个清晰、明确的结果。在ISMIR 2011竞赛数据集上验证了提出的基于多核学习支持向量机(MKL-SVM)的分类方法,并与传统的基于单核支持向量机的方法进行了比较分析。实验结果表明基于MKL-SVM的音乐流派自动分类准确率比传统单核支持向量机的分类准确率提高了6.58%,且该方法与传统的特征选择结果比较,更清楚地解释了所选择的特征向量对流派分类的影响大小,通过选择影响较大的特征组合进行分类,分类结果也有了明显的提升。     

Comparison of ISFs and LSFs in Speech/Music Discrimination System

The immittance spectral frequencies （ISFs） is proposed as a new set of classification features and compared with the linear spectral frequencies （LSFs） applied in a frame-level wideband speech/music discrimination system. These two sets of features can be shared by the classifier and coding module to reduce the total computational complexity, making our classification system suitable for multi-mode audio coding applications. A performance assessment and comparison of the features are made. The experiment results show that the ISFs and LSFs have similar good performance when using full covariance matrices in classification models and the ISFs perform slightly better when using diagonal matrices. Their statistical differences for speech and music signals are also revealed.     

中国碟片包装设计探讨

探讨了我国碟片包装中存在于题材、内涵、碟片内外包装等方面的问题,通过拓宽设计范围,更加注重封套设计表现音乐内涵及艺术感受,统一封套、内页、盘面及外盒包装,展现出唱片包装的独特性,达到碟片包装的艺术性与功能性的高度统一效果.     

Locomotor expertise predicts infants’ perseverative errors.

This research examined the development of inhibition in a locomotor context. In a within-subjects design, infants received high- and low-demand locomotor A-not-B tasks. In Experiment 1, walking 13-month-old infants followed an indirect path to a goal. In a control condition, infants took a direct route. In Experiment 2, crawling and walking 13-month-old infants crawled through a tunnel to reach a goal at the other end and received the same control condition as in Experiment 1. In both experiments, perseverative errors occurred more often in the high-demand condition than in the low-demand condition. Moreover, in Experiment 2, walkers perseverated more than crawlers, and extent of perseveration was related to infants’ locomotor experience. In Experiment 3, the authors addressed a possible confound in Experiment 2 between locomotor expertise and locomotor posture. Novice crawlers perseverated in the difficult tunnels condition, behaving more like novice walkers than expert crawlers. As predicted by a cognitive capacity account of infant perseveration, overtaxed attentional resources resulted in a cognition–action trade-off. Experts who found the task less motorically effortful than novices had more cognitive resources available for problem solving. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

面向推荐系统的音乐特征抽取

音乐推荐系统是指根据用户的历史浏览数据,从候选库中推荐给用户可能喜欢的音乐的一种新型网络服务。该系统的关键在于需要对整个数据库按照音乐风格进行分类,基于此提出一种新的音乐特征处理方法来完成音乐库分类,以有效实现音乐推荐。该方法首先为候选音乐库构建常规的音乐特征数据集,然后基于分形理论对数据集进行属性约简,获取每一首音乐的推荐特征向量,并且依据特征向量的特点,定义了一种新的距离度量方法。在包含六种风格的音乐数据库的实验中,仿真结果证明了提出的音乐推荐特征和距离度量的有效性,与现有的基于内容的音乐检索研究相比,音乐推荐特征的使用极大地降低了对数据库存储量的需求,对音乐推荐系统的网络开发具有很好的应用价值。     

基于谐波的乐纹提取和音乐检索

提出了一种基于节拍内音乐谐波特性的乐纹特征提取方法,首先求得每帧音乐的谐波信息,再利用跟踪得到的节拍,计算节拍内所有帧的谐波信息的均值,构成此节拍的乐纹特征矩阵。为了提高音乐检索的效率,设计了一个二级音乐检索算法：根据节拍信息,将与查询音乐片段的每分钟节拍数相近的音乐作为候选音乐,再逐节拍计算所查询音乐的乐纹和候选音乐乐纹的相似度,选择相似度最高的音乐作为检索结果。实验结果表明,提出的乐纹特征和音乐检索算法有效地提高了检索准确率和检索效率。     

Two‐pass search strategy using accumulated band energy histogram for HMM‐based identification of perceptually identical music

In this article, we present an efficient two‐pass search strategy for the implementation of a Hidden Markov Model (HMM)‐based music identification system. In our previous work, we demonstrated a single‐pass HMM‐based music identification system, considering its application to music copyright protection. This conventional system showed very robust performance to signal‐level variations between perceptually identical music files. However, it requires heavy computation for search. In the proposed two‐pass search system, the conventional single‐pass search is extended to two‐pass. In pass 1 of the proposed method, a queried music produces an accumulated band energy histogram which is a set of normalized sums of band energies for each frequency bin. This histogram is compared to all of the histograms for the registered music files. The system generates a list of small number of most probable music files among the all of the registered music files. In pass 2, HMM‐based search is applied only to candidate music files selected in pass 1. Using the proposed two‐pass strategy, we successfully implemented a HMM‐based music identification system, which maintains the same level robustness to signal level variations between perceptually identical music files but also produces the identification result very quickly. © 2013 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 23, 127–132, 2013     

柔和背景音乐对脑力劳动绩效的影响

该文采用17项神经行为能力测试,定量地测量人员的感知、记忆、推理等多方面能力,并结合对情绪、烦躁度以及头疼等病态综合症状的主观问卷调查,通过实验研究了柔和背景音乐对人员脑力劳动绩效的影响。结果表明,柔和、慢节奏的背景音乐对人员脑力劳动绩效和情绪没有积极作用,相反,在背景音乐环境下受试者的不舒适、耳痛和头疼症状有所增加,其复杂脑力劳动任务的绩效显著下降。因此,对从事复杂的、认知资源需求较高的脑力劳动的人,其工作环境中不宜添加背景音乐。