A fast audio similarity retrieval method for millions of music tracks

We present a filter-and-refine method to speed up nearest neighbor searches with the Kullback–Leibler divergence for multivariate Gaussians. This combination of features and similarity estimation is of special interest in the field of automatic music recommendation as it is widely used to compute music similarity. However, the non-vectorial features and a non-metric divergence make using it with large corpora difficult, as standard indexing algorithms can not be used. This paper proposes a method for fast nearest neighbor retrieval in large databases which relies on the above approach. In its core the method rescales the divergence and uses a modified FastMap implementation to speed up nearest-neighbor queries. Overall the method accelerates the search for similar music pieces by a factor of 10–30 and yields high recall values of 95–99% compared to a standard linear search.     

Music composition by interaction between human and computer

This paper aims at constructing a music composition system that composes music by the interaction between human and a computer. Even users without special musical knowledge can compose 16-bar musical works with one melody part and some backing parts using this system. The interactive Genetic Algorithm is introduced to music composition so that users’ feeling toward music is reflected in the composed music. One chromosome corresponds to 4-bar musical work information. Users participate in music composition by evaluating composed works after GA operators such as crossover, mutation, virus infection are applied to chromosomes based on the evaluation results. From the experimental results, it is found that the users’ evaluation values become high over the progress of generations. That is, the system can compose 16-bar musical works reflecting users’ feeling. Muneyuki Unehara: He received his M.S. in Engineering in 2002 from Institute of Science and Engineering, University of Tsukuba. Currently, he is a Ph.D. candidate of Graduate School of Systems and Information Engineering, University of Tsukuba. His research interests include the construction of intelligent systems by considering soft computing techniques and human interface. Takehisa Onisawa, Ph.D.: He received Dr.Eng. in Systems Science in 1986 from Tokyo Institute of Technology. Currently, he is a Professor in the Graduate School of Systems and Information Engineering, University of Tsukuba. His research interests include applications of soft computing techniques to human centered systems thinking. He is a member of IEEE and IFSA.     

Musical creativity in collaborative virtual environments

A review of musical creativity in collaborative virtual environments (CVE) shows recurring interaction metaphors that tend from precise control of individual parameters to higher level gestural influence over whole systems. Musical performances in CVE also show a consistent re-emergence of a unique form of collaboration called “melding” in which individual virtuosity is subsumed to that of the group. Based on these observations, we hypothesized that CVE could be a medium for creating new forms of music, and developed the audiovisual augmented reality system (AVIARy) to explore higher level metaphors for composing spatial music in CVE. This paper describes the AVIARy system, the initial experiments with interaction metaphors, and the application of the system to develop and stage a collaborative musical performance at a sound art concert. The results from these experiments indicate that CVE can be a medium for new forms of musical creativity and distinctive forms of music.     

Higher-Order Gauss–Lobatto Integration for Non-Linear Hyperbolic Equations

Least-squares spectral elements are capable of solving non-linear hyperbolic equations, in which discontinuities develop in finite time. In recent publications [De Maerschalck, B., 2003, http://www.aero.lr.tudelft.nl/∼bart; De Maerschalck, B., and Gerritsma, M. I., 2003, AIAA; De Maerschalck, B., and Gerritsma, M. I., 2005, Num. Algorithms, 38(1–3); 173–196], it was noted that the ability to obtain the correct solution depends on the type of linearization, Picard’s method or Newton linearization. In addition, severe under-relaxation was necessary to reach a converged solution. In this paper the use of higher-order Gauss–Lobatto integration will be addressed. When a sufficiently fine GL-grid is used to approximate the integrals involved, the discrepancies between the various linearization methods are considerably reduced and under-relaxation is no longer necessary     

Content-based audio classification and retrieval using a fuzzy logic system: towards multimedia search engines

 In recent years, available audio corpora are rapidly increasing from fast growing Internet and digital libraries. How to classify and retrieve sound files relevant to the user's interest from large databases is crucial for building multimedia web search engines. In this paper, content-based technology has been applied to classify and retrieve audio clips using a fuzzy logic system, which is intuitive due to the fuzzy nature of human perception of audio, especially audio clips with mixed types. Two features selected from various extracted features are used as input to a constructed fuzzy inference system (FIS). The outputs of the FIS are two types of hierarchical audio classes. The membership functions and rules are derived from the distributions of extracted audio features. Speech and music can thus be discriminated by the FIS. Furthermore, female and male speech can be separated by another FIS, whereas percussion can be distinguished from other music instruments. In addition, we can use multiple FISs to form a “fuzzy tree” for retrieval of more types of audio clips. With this approach, we can classify and retrieve generic audios more accurately, using fewer features and less computation time, compared to other existing approaches.     

Motion segmentation and pose recognition with motion history gradients

This paper presents a fast and simple method using a timed motion history image (tMHI) for representing motion from the gradients in successively layered silhouettes. This representation can be used to (a) determine the current pose of the object and (b) segment and measure the motions induced by the object in a video scene. These segmented regions are not “motion blobs”, but instead are motion regions that are naturally connected to parts of the moving object. This method may be used as a very general gesture recognition “toolbox”. We demonstrate the approach with recognition of waving and overhead clapping motions to control a music synthesis program. Accepted: 13 August 2001     

Sentient map – a new paradigm for visual computing

 A sentient map enables the user to view a collection of information items as a map so that gestures, or more specifically c-gestures, can be used for the interaction between the user and the information system. Different c-gestures are dynamically transformed into spatial/temporal queries, or σ-queries, for accessing the information items in multimedia databases and data sources. An application in e-learning called the Growing Book is described. The visual computing paradigm offered by the sentient map can be summarized as follows: “I come, I see, I gesture”.     

Technology scruples: why intimidation will not save the recording industry and how enchantment might

While the recording industry continues to lobby for increasingly draconian laws to protect their interests, users of digital technology continue to share files and copy protected music. This paper considers the ethics of copying and argues that legal measures are unlikely to solve the music industry’s problems in the age of digital reproduction. It begins with a review of the legal arguments around copyright legislation and notes that the law is currently unclear and contested. Adapting the game “scruples” to questions of what is and is not considered theft, a qualitative study reflects on the ways that ethical positions around new media are reached and articulated. The findings relate ethical positions constructed around notions of resistance, intangibility and identity. It is argued that the global online population cannot be policed without consent and that mechanics of artist reimbursement must be developed that account for consumers’ technology scruples. File sharing is then considered not as a legal problem but as a design challenge and a strategy of enchantment is suggested. The design concept of a digital music box is outlined to illustrate strategies of enchantment rather than litigation and intimidation.     

Tune in to your emotions: a robust personalized affective music player

The emotional power of music is exploited in a personalized affective music player (AMP) that selects music for mood enhancement. A biosignal approach is used to measure listeners’ personal emotional reactions to their own music as input for affective user models. Regression and kernel density estimation are applied to model the physiological changes the music elicits. Using these models, personalized music selections based on an affective goal state can be made. The AMP was validated in real-world trials over the course of several weeks. Results show that our models can cope with noisy situations and handle large inter-individual differences in the music domain. The AMP augments music listening where its techniques enable automated affect guidance. Our approach provides valuable insights for affective computing and user modeling, for which the AMP is a suitable carrier application.     

Dennett’s Overlooked Originality

 No philosopher has worked harder than Dan Dennett to set the possibility of machine mentality on firm philosophical footing. Dennett’s defense of this possibility has both a positive and a negative thrust. On the positive side, he has developed an account of mental activity that is tailor-made for the attribution of intentional states to purely mechanical contrivances, while on the negative side, he pillories as mystery mongering and skyhook grasping any attempts to erect barriers to the conception of machine mentality by excavating gulfs to keep us “bona fide” thinkers apart from the rest of creation. While I think he’s “won” the rhetorical tilts with his philosophical adversaries, I worry that Dennett’s negative side sometimes gets the better of him, and that this obscures advances that can be made on the positive side of his program. In this paper, I show that Dennett is much too dismissive of original intentionality in particular, and that this notion can be put to good theoretical use after all. Though deployed to distinguish different grades of mentality, it can (and should) be incorporated into a philosophical account of the mind that is recognizably Dennettian in spirit.     

Editorial

At the time of writing this editorial, subscribers will have just received their copies of the triple issue honouring the work of Rod Burstall. Coordinating this collection was a substantial undertaking; and thanks go to all concerned, particularly to David Rydeheard and Don Sannella and the behind the scenes production staff. We (the journal editors) hope you agree that it was well worth waiting for the fascinating collection. The production and scheduling of that set of papers, and other incidental but cumulative factors, have contributed to recent issues being late. We hope soon to be back close to our planned, evenly timed, publication timetable; however it also seems timely to mention, and to reiterate, some changes which are afoot. As of this issue (14.1) we shall revert to our initial publication frequency of 4 issues per year, but these will be larger than in earlier volumes and will retain the large page format adopted in Volume 12. [A reminder for authors who use LaTeX to use the new class files.] We are now receiving, and publishing, long papers (but still with the option of including supplementary material on the web) and, except in special issues, strive to achieve a reasonable coverage of topics within the given constraints. Although normally skipped over, readers of the journal front matter might notice periodic changes to the editorial board. These usually go unmentioned; our editors (who are working editors, not merely ‘names’) seek no reward or praise. Readers will also notice the recently modernised BCS-FACS logo and a declaration that the journal (although truly international in scope) was founded by (BCS-)FACS, some even to this day refer to it as ‘the FACS journal’, and we are very happy for this to continue. Bringing these two threads together gets me to the point of this digression. Dan Simpson founded the BCS specialist group on Formal Aspects of Computing Science some 25 years ago. Without his radical suggestion that the BCS had a specialist group that actually addressed Computer Science, there would have been no FACS and no FACS journal. Dan has recently finished his spell as Dean in the Faculty of IT at Brighton University and he has also resigned as a member of our editorial board. As you can see, he was active to the very end being responsible for progressing 2 of the 3 papers in this issue. I gather he now intends to concern himself with other matters; I would counsel a less stressful life and more Bob Dylan music. He has been a friend and colleague of many of those associated with the FACS group and its journal; on their behalf may I offer a big ‘thank you’ for all that you have done for us and offer our best wishes for whatever endeavours you are about to embark upon. Very many years ago, at a conference, I heard someone respond in debate “I didn't see who said that but it sounded like Mr Simpson from Teesside … .” – well it's no longer ‘Mr’ nor ‘Teesside’ but I can't believe that we really have seen or heard the last of this Yorkshire lad. Thanks, goodbye and good luck. It is with deep regret that we have to report the death of Ole-Johan Dahl. Professor Dahl was a leader of thought in many fields; his contributions on Object-Oriented languages and methods were recently recognised in his (joint) awards of the IEEE von Neumann prize and the ACM Turing Award. He was also a major contributor to Formal Methods and a future edition of this journal will attempt to mark his contribution. We have lost an editor; our thoughts are with his family who have lost so much more.au     

Generating novel memories by integration of chaotic neural network modules

A principle of integrating neural network modules based on chaotic dynamics was studied on our two-moduled Nozawa model. Chaotic neural networks represent each embedded pattern as a low-dimensional periodic orbit, and the others are shown as high-dimensional chaotic attractors. This is equivalent to W. Freeman’s “I don’t know” and “I know” states. In particular, we noted that the combination of two-way inputs to each neural network module conflicted with embedded Hebbian correspondence. It was found that the interaction between the modules generated a novel “I know” state in addition to the embedded representation. Chaotic neural network modules can autonomously generate novel memories or functions by this interaction. The result suggests a functional integration in neural networks as it ought to be, e.g., feature binding and gestalt. This work was presented, in part, at the Fourth International Symposium on Artificial Life and Robotics, Oita, Japan, January 19–22, 1999     

Relational IBL in classical music

It is well known that many hard tasks considered in machine learning and data mining can be solved in a rather simple and robust way with an instance- and distance-based approach. In this work we present another difficult task: learning, from large numbers of complex performances by concert pianists, to play music expressively. We model the problem as a multi-level decomposition and prediction task. We show that this is a fundamentally relational learning problem and propose a new similarity measure for structured objects, which is built into a relational instance-based learning algorithm named DISTALL. Experiments with data derived from a substantial number of Mozart piano sonata recordings by a skilled concert pianist demonstrate that the approach is viable. We show that the instance-based learner operating on structured, relational data outperforms a propositional k-NN algorithm. In qualitative terms, some of the piano performances produced by DISTALL after learning from the human artist are of substantial musical quality; one even won a prize in an international ‘computer music performance’ contest. The experiments thus provide evidence of the capabilities of ILP in a highly complex domain such as music. Editors: Tamás Horváth and Akihiro Yamamoto     

RoboMusic: a behavior-based approach

Based on principles from modern artificial intelligence and robotics, we developed the RoboMusic concept. In RoboMusic, we use a number of robotic devices as instruments, and the tunes are composed as a behavior-based system. The music artist composes a baseline behavior for the robotic instruments, and composes the behavioral response to interactions by human musicians. The music artist is transformed from a composer of static music tunes to a developer of robot behavior: behavior that is expressed by the robotic system as music pieces. Music compositions are transformed to become robotic behavior as in a behavior-based system. A RoboMusic concert is performed with robotic instruments, and changes the concept of live concerts by inviting the audience to interact with the band’s instruments themselves and thereby guide the live performance of the music themselves. This work was presented in part at the 12th International Symposium on Artificial Life and Robotics, Oita, Japan, January 25–27, 2007     

User-centred process for the definition of free-hand gestures applied to controlling music playback

Music is a fundamental part of most cultures. Controlling music playback has commonly been used to demonstrate new interaction techniques and algorithms. In particular, controlling music playback has been used to demonstrate and evaluate gesture recognition algorithms. Previous work, however, used gestures that have been defined based on intuition, the developers’ preferences, and the respective algorithm’s capabilities. In this paper we propose a refined process for deriving gestures from constant user feedback. Using this process every result and design decision is validated in the subsequent step of the process. Therefore, comprehensive feedback can be collected from each of the conducted user studies. Along the process we develop a set of free-hand gestures for controlling music playback. The situational context is analysed to shape the usage scenario and derive an initial set of necessary functions. In a successive user study the set of functions is validated and proposals for gestures are collected from participants for each function. Two gesture sets containing static and dynamic gestures are derived and analysed in a comparative evaluation. The comparative evaluation shows the suitability of the identified gestures and allows further refinement. Our results indicate that the proposed process, that includes validation of each design decision, improves the final results. By using the process to identify gestures for controlling music playback we not only show that the refined process can successfully be applied, but we also provide a consistent gesture set that can serve as a realistic benchmark for gesture recognition algorithms.     

Contextual patterns in mobile service usage

Mobile services differ from other services because of their temporal and spatial attributes. Mobile services additionally differ from each other in their value-added to the end-user. Some services—such as emailing and voice—are more business oriented. On the other hand, various free-time oriented services are provided in new smartphones, such as imaging and music playback. The present paper studies how mobile services are used in different contexts. For this, the paper develops a specialized algorithm that can be used with handset-based usage data acquired straight from end-users in an established panel study process. Educated guesses can be drawn on the user context based on the developed algorithm. In the present exercise usage contexts were divided into home, office and “on the move”. The algorithm is used with exemplary data from Finland and the UK covering 324 consumers in 2006. More than 70% of contextual use cases are correctly classified based on raw data. According to exemplary results particularly multimedia services are used “on the move”, whereas legacy mobile services experience more evenly distributed usage across all contexts. The algorithm that identifies context based on raw data provides a new angle to mobile end-user research. In the future, the accuracy of the algorithm will be improved with the integration of seamless cell-id logging and GPS data.     

基于PIC单片机PWM模式的音乐播放系统设计

针对51单片机I/O定时翻转电平驱动蜂鸣器方法存在的缺点,以PIC单片机为核心控制元件,利用内部PWM硬件资源,实现了简易音乐播放系统设计。通过改变PWM端口输出脉冲信号频率及脉宽,驱动蜂呜器发出不同音调,并结合单片机内部定时器中断控制音调高低及节拍长度,此外可通过4×4矩阵键盘实现简单音乐弹奏。实验结果表明,该系统硬件电路简单,软件占用CPU时间少,易控制音乐音调及节拍,音色纯正,具有一定的实用与参考价值。     

A Note on Non-Deterministic Communication Complexity with Few Witnesses

We improve both main results of the paper ``Non-Deterministic Communication Complexity with Few Witnesses ' by M. Karchmer, I. Newman, M. Saks, and A. Wigderson, that appeared in Journal of Computer and System Sciences , Vol. 49, pp. 247—257.