Higher-order moments for musical genre classification

This paper presents a study on the performance of the higher-order moments for musical genre classification. Especially the skewness and the kurtosis of the octave-scale subbands are considered. Experimental results on the widely used music datasets show that the higher-order moment features can improve classification accuracy when combined with the conventional lower-order moment features.     

Neural networks for classification: a survey

Classification is one of the most active research and application areas of neural networks. The literature is vast and growing. This paper summarizes some of the most important developments in neural network classification research. Specifically, the issues of posterior probability estimation, the link between neural and conventional classifiers, learning and generalization tradeoff in classification, the feature variable selection, as well as the effect of misclassification costs are examined. Our purpose is to provide a synthesis of the published research in this area and stimulate further research interests and efforts in the identified topics     

声乐主旋律的自动提取

提出一种基于多候选基频提取和歌声基频判别的声乐主旋律提取算法。该算法可以有效降低旋律定位虚警率,提高整体准确率。利用度量距离(DIS)算法对音乐进行音符切分,并用方差法实现浊音段检测;采用幅度压缩基音估计滤波器(PEFAC)多基频提取技术,通过计算音高显著度提取每个浊音帧的多个候选基频。最后用维特比算法跟踪浊音段主导基频轨迹,并用基频判别模型进行歌声主旋律判别。在MIR-1K数据集上进行的实验表明,在信干比为5 dB和0 dB的情况下,本文算法提取的声乐主旋律整体准确率分别达到了86.22%和77.4%,相比于其他算法至少提高了3.79%和2.01%。     

A semantic framework for video genre classification and event analysis

Semantic video analysis is a key issue in digital video applications, including video retrieval, annotation, and management. Most existing work on semantic video analysis is mainly focused on event detection for specific video genres, while the genre classification is treated as another independent issue. In this paper, we present a semantic framework for weakly supervised video genre classification and event analysis jointly by using probabilistic models for MPEG video streams. Several computable semantic features that can accurately reflect the event attributes are derived. Based on an intensive analysis on the connection between video genres and the contextual relationship among events, as well as the statistical characteristics of dominant event, a hidden Markov model (HMM) and naive Bayesian classifier (NBC) based analysis algorithm is proposed for video genre classification. Another Gaussian mixture model (GMM) is built to detect the contained events using the same semantic features, whilst an event adjustment strategy is proposed according to an analysis on the GMM structure and pre-definition of video events. Subsequently, a special event is recognized based on the detected events by another HMM. The simulative experiments on video genre classification and event analysis using a large number of video data sets demonstrate the promising performance of the proposed framework for semantic video analysis.     

Signal processing aspects of computer music: A survey

The application of modern signal processing techniques to the production and processing of musical sound gives the composer and musician a level of freedom and precision of control never before obtainable. This paper surveys the use of analyis of natural sounds for synthesis, the use of speech and vocoder techniques, methods of artificial reverberation, the use of discrete summation formulae for highly efficient synthesis, the concept of the all-digital recording studio, and discusses the role of special-purpose hardware in digital music synthesis, illustrated with two unique digital music synthesizers.     

Automatic structure detection for popular music

Our proposed approach detects music structures by looking at beat-space segmentation, chords, singing-voice boundaries, and melody- and content-based similarity regions. Experiments illustrate that the proposed approach is capable of extracting useful information for music applications.     

FPGA-based implementation of classification techniques: A survey

Recently, a number of classification techniques have been introduced. However, processing large dataset in a reasonable time has become a major challenge. This made classification task more complex and expensive in calculation. Thus, the need for solutions to overcome these constraints such as field programmable gate arrays (FPGAs). In this paper, we give an overview of the various classification techniques. Then, we present the existing FPGA based implementation of these classification methods. After that, we investigate the confronted challenges and the optimizations strategies. Finally, we highlight the hardware accelerator architectures and tools for hardware design suggested to improve the FPGA implementation of classification methods.     

基于情感特征的背景音乐分类方法

为了准确描述背景音乐的类别,提出基于情感特征的背景音乐分类方法。针对当前方法没有考虑情感特征的缺陷,提取情感特征,并与其他特征进行融合组成背景音乐分类特征向量,然后对特征进行筛选,作为神经网络的输入向量,最后采用神经网络进行自动学习,建立背景音乐分类器,并对具体背景音乐数据进行分类和识别。实验结果表明,该方法能够准确区别各种背景音乐,分类正确率高达98%以上,同时也可以应用于其他音乐的分类,具有良好的推广性。     

Emotion classification during music listening from forehead biosignals

Emotion recognition systems are helpful in human–machine interactions and clinical applications. This paper investigates the feasibility of using 3-channel forehead biosignals (left temporalis, frontalis, and right temporalis channel) as informative channels for emotion recognition during music listening. Classification of four emotional states (positive valence/low arousal, positive valence/high arousal, negative valence/high arousal, and negative valence/low arousal) in arousal–valence space was performed by employing two parallel cascade-forward neural networks as arousal and valence classifiers. The inputs of the classifiers were obtained by applying a fuzzy rough model feature evaluation criterion and sequential forward floating selection algorithm. An averaged classification accuracy of 87.05 % was achieved, corresponding to average valence classification accuracy of 93.66 % and average arousal classification accuracy of 93.29 %.     

Security issues and solutions in multicast content distribution: a survey

Multicast enables efficient large-scale content distribution by providing an efficient transport mechanism for one-to-many and many-to-many communication. The very properties that make multicast attractive, however, also make it a challenging environment in which to provide content security. We show how the fundamental properties of the multicast paradigm cause security issues and vulnerabilities. We focus on four areas of research in security for multicast content distribution: receiver access control, group key management, multicast source authentication, and multicast fingerprinting. For each we explain the vulnerabilities, discuss the objectives of solutions, and survey work in the area. Also, we briefly highlight other security issues in multicast content distribution including source access control, secure multicast routing, and group policy specification. We then outline several future research directions.     

Automatic classification of high frequency signals

The discovery of the possibility to transmit information by electromagnetic waves led to the appreciation of the importance of such wireless transmissions and subsequently to the requirement for monitoring these radio emissions. Radio monitoring is particularly important in the high frequency range (3 MHz … 30 MHz) because no fixed channel pattern exists in the short wave band. One task of a radio monitoring device detecting signals transmitted by short wave radio stations could well be the automatic determination of the transmitters modulation mode. One may consider this task to represent a pattern recognition problem and use of methods of digital signal processingand pattern recognition for its solution.     

一种基于音调的语音/音乐实时分类算法

语音／音乐的实时分类,在语音／音乐通用编码器中是尤其重要的。分析了语音和音乐的区别性特征,提出了一种利用音调分布特性和频谱倾斜度对语音和音乐进行实时分类的算法,并对分类结果进行简单平滑,使分类更为合理,从而提高音质。实验结果表明,此算法复杂度低,而且分类准确率高,实用性强。     

基于DBN的多模态音乐情感分类研究

文中提出了一种将音频与歌词两种模态结合并利用深度置信网络进行音乐情感分类的方法。在分类器的选择上,将传统的分类器用DBN进行了替换,且改进了子任务结合晚融合法(LFSM)来完成多模态的融合,并验证了该方法的可行性。实验结果表明,该方法对音乐情感分类效果较好,高于基于单一模态和传统分类器的分类方法。     

应用于音乐节目分类的Apriori挖掘算法设计

传统Apriori挖掘算法需多次扫描数据库、多次连接频繁项集,导致挖掘效率较低,为此对Apriori挖掘算法加以改进,设计一种新的Apriori挖掘算法用于音乐节目分类。改进的Apriori挖掘算法采用莱特准则对音频数据进行野值与噪声平滑处理,改进Apriori挖掘算法的音频数据库映射令两个线性表分别负责音频数据存储和对应项存储,音频数据库扫描次数降为一次;改进Apriori挖掘算法的连接次数无需对不具备交运算能力的元素进行交运算操作,减少频繁项集连接次数。基于改进频繁项集Apriori挖掘算法挖掘频繁项集、生成音频数据关联规则,基于关联规则集构建分类器,实现音乐节目分类。实验结果显示,改进Apriori挖掘算法用于音乐节目分类的效率优势突出,准确度高。     

Automatic segmentation and classification of ionic-channel signals

Identification of ionic-channel types and their selectivity depends critically on the open channel current that can be resolved. In this paper, an automatic channel detection algorithm is proposed that is based on sequential minimization of an index which is usually used in cluster analysis. The algorithm consists of two stages, namely segmentation and classification. In the first stage, the signal samples are segmented based on the assumption that the samples in each segment should be sequentially connected. In the second stage, the resultant segments are classified with no regard to their connectivities. Results on synthetic and real channel currents are very encouraging and they suggest that this algorithm will substantially increase the productivity of many laboratories involved in ionic-channel research.     

改进极限学习机的电子音乐分类模型

针对传统模型无法准确实现电子音乐分类和识别的难题,提出改进极限学习机的电子音乐分类模型。首先对电子音乐数据进行采集,并提取其倒谱系数特征,并采用核主成分分析对特征进行筛选;然后采用遗传算法对极限学习机的参数进行选择,并用于构建电子音乐的分类器;最后采用多种类型的电子音乐进行仿真实验,改进极限学习机的电子音乐平均分类率达到了95%以上,电子音乐的错分率要远远低于当前其他电子音乐分类模型。实验结果验证了该电子音乐分类模型的可行性以及优越性。     

基于优化神经网络的音乐分类模型研究

为高效、精准地判断音乐风格归属,帮助用户快速获取偏好音乐风格,基于群智优化神经网络构建音乐风格分类模型。提取音乐样本的音质、节奏、旋律特征作为模型训练样本输入BP神经网络,通过初始化、隐含层及输出层计算、权值计算等步骤完成神经网络模型训练。采用粒子群算法确定神经网络的最优权值与阈值,粒子群算法首先编码神经网络权值与阈值,其次计算粒子适应度值,更新粒子速度和位置,符合终止条件时输出神经网络的权值与阈值优化结果,并据此构建基于群智优化神经网络的音乐风格分类模型。模型测试结果表明,所提模型在正确区分不同音乐风格的同时,展示了音质、节奏、旋律等特征。     

Musical instrument classification and duet analysis employing music information retrieval techniques

The aim of this paper is to present solutions related to identifying musical data. These are discussed mainly on the basis of experiments carried out at the Multimedia Systems Department, Gdansk University of Technology, Gdansk, Poland. The topics presented in this paper include automatic recognition of musical instruments and separation of duet sounds. The classification process is shown as a three-layer process consisting of pitch extraction, parametrization, and pattern recognition. These three stages are discussed on the basis of experimental examples. Artificial neural networks (ANNs) are employed as a decision system and they are trained with a set of feature vectors (FVs) extracted from musical sounds recorded at the Multimedia Systems Department. The frequency envelope distribution (FED) algorithm is presented, which was introduced to musical duet separation. For the purpose of checking the efficiency of the FED algorithm, ANNs are also used. They are tested on FVs derived from musical sounds after the separation process is performed. The experimental results are shown and discussed.     

Automatic system for quality-based classification of marble textures

In this paper, we present an automatic system and algorithms for the classification of marble slabs into different groups in real time in production line, according to slabs quality. The application of the system is aimed at the marble industry, in order to automate and improve the manual classification process of marble slabs carried out at present. The system consists of a mechatronic prototype, which houses all the required physical components for the acquisition of marble slabs images in suitable light conditions, and computational algorithms, which are used to analyze the color texture of the marble surfaces and classify them into their corresponding group. In order to evaluate the color representation influence on the image analysis, four color spaces have been tested: RGB, XYZ, YIQ, and K-L. After the texture analysis performed with the sum and difference histograms algorithm, a feature extraction process has been implemented with principal component analysis. Finally, a multilayer perceptron neural network trained with the backpropagation algorithm with adaptive learning rate is used to classify the marble slabs in three categories, according to their quality. The results (successful classification rate of 98.9%) show very high performance compared with the traditional (manual) system.