Information and Communication Technology

The shaping of future generations depends on an education system that aims at a holistic development of a student. This paper proposes an education model which is a mixture of a traditional educational system and the latest technological advancements. The Gurukul way of learning was pioneered and practised by early Indians; we have discussed, in this paper, some illustrative examples of how the practise led shape to a more complete student. The current education system has a shift from quality education to education to the masses. The central figure of Guru, who would imbibe in his students both knowledge and character, is also lost. The Gurukul tradition provided a more personalized learning experience where the Guru would judge his pupil and understand his strengths and weaknesses. An ideal system would be one that provides a personalized learning experience to everyone. Such a system in our modern times is only possible by using the technological advancements available, in partic...

Music and speech detection provides us valuable information regarding the nature of content in broadcast audio. It helps detect acoustic regions that contain speech, voice over music, only music, or silence. In recent years, there have been developments in machine learning algorithms to accomplish this task. However, broadcast audio is generally well-mixed and copyrighted, which makes it challenging to share across research groups. In this study, we address the challenges encountered in automatically synthesising data that resembles a radio broadcast. Firstly, we compare state-of-the-art neural network architectures such as CNN, GRU, LSTM, TCN, and CRNN. Later, we investigate how audio ducking of background music impacts the precision and recall of the machine learning algorithm. Thirdly, we examine how the quantity of synthetic training data impacts the results. Finally, we evaluate the effectiveness of synthesised, real-world, and combined approaches for training models, to unders...

Brain-computer interfaces (BCIs) are beneficial for patients who are suffering from motor disabilities because it offers them a way of creative expression, which improves mental well-being. BCIs aim to establish a direct communication medium between the brain and the computer. Therefore, unlike conventional musical interfaces, it does not require muscular power. This paper explores the potential of building sound synthesisers with BCIs that are based on steady-state visually evoked potential (SSVEP). It investigates novel ways to enable patients with motor disabilities to express themselves. It presents a new concept called sonic expression, that is to express oneself purely by the synthesis of sound. It introduces new layouts and designs for BCI-based sound synthesisers and the limitations of these interfaces are discussed. An evaluation of different sound synthesis techniques is conducted to find an appropriate one for such systems. Synthesis techniques are evaluated and compared ...

Brain-computer interfaces (BCIs) aim to establish a communication medium that is independent of muscle control. This project investigates how BCIs can be harnessed for musical applications. The impact of such systems is twofold — (i) it offers a novel mechanism of control for musicians during performance and (ii) it is beneficial for patients who are suffering from motor disabilities. Several challenges are encountered when attempting to move these technologies from laboratories to real-world scenarios. Additionally, BCIs are significantly different from conventional computer interfaces and realise low communication rates. This project considers these challenges and uses a dry and wireless electroencephalogram (EEG) headset to detect neural activity. It adopts a paradigm called steady state visually evoked potential (SSVEP) to provide the user with control. It aims to encapsulate all braincomputer music interface (BCMI)-based operations into a stand-alone application, which would im...

Audio segmentation and sound event detection are crucial topics in machine listening that aim to detect acoustic classes and their respective boundaries. It is useful for audiocontent analysis, speech recognition, audio-indexing, and music information retrieval. In recent years, most research articles adopt segmentation-by-classification. This technique divides audio into small frames and individually performs classification on these frames. In this paper, we present a novel approach called You Only Hear Once (YOHO), which is inspired by the YOLO algorithm popularly adopted in Computer Vision. We convert the detection of acoustic boundaries into a regression problem instead of frame-based classification. This is done by having separate output neurons to detect the presence of an audio class and predict its start and end points. YOHO obtained a higher F-measure and lower error rate than the state-of-the-art Convolutional Recurrent Neural Network on multiple datasets. As YOHO is purel...

Creative systems such as algorithmic composers often use Artificial Intelligence models like Markov chains, Neural Networks, and Genetic Algorithms to model stochastic processes. Unconventional Computing (UC) technologies explore non-digital ways of data storage, processing, input, and output. UC paradigms such as Biocomputing and Quantum Computing delve into domains beyond the binary bit to handle complex non-linear functions. In this paper, we harness Physarum polycephalum as a memristor to process and generate creative data for popular music. The organism works as a collaborator in the process of composing our song titled Creep into my Lawn. While there has been research conducted in this area, the literature lacks examples of popular music and how the organism’s non-linear behaviour can be controlled while composing music. This is important because non-linear forms of representation are not as obvious as conventional digital means. This study aims at disseminating this technolog...

Our research concerns the development of biocomputers using electronic components grown out of biological material. This paper reports the development of an unprecedented biological memristor and an approach to using such a biomemristors to build interactive generative music systems. The memristor is a relatively less well-known electronic component regarded as a resistor with memory. After an introduction to harnessing the Physarum polycephalum organism to implement biomemristors, the paper presents PhyBox: a biocomputer that uses four biomemristors to generate music interactively. The resistance of a biomemristor varies in function of voltage that has passed through it. Music input is represented in terms of voltage transitions and music output is encoded as measurements of current yielded by the system's memristive behaviour. An example of a musical composition using PhyBox is detailed. The paper concludes with a short discussion on how the combination between artificial Miranda, Braund and Venkatesh 3 Computer Music Journal machines and biological organisms is paving the way for the development of new technologies for music based on living processors.