In the context of the Internet of Things, sound sensing applications are required to run on embedded platforms where notions of product pricing and form factor impose hard constraints on the available computing power. Whereas Automatic Environmental Sound Recognition (AESR) algorithms are most often developed with limited consideration for computational cost, this paper seeks which AESR algorithm can make the most of a limited amount of computing power by comparing the sound classification performance as a function of its computational cost. Results suggest that Deep Neural Networks yield the best ratio of sound classification accuracy across a range of computational costs, while Gaussian Mixture Models offer a reasonable accuracy at a consistently small cost, and Support Vector Machines stand between both in terms of compromise between accuracy and computational cost.

This paper addresses the question of how to extend the capabilities of a well-established interface in a way that respects users' existing expertise. The piano-style keyboard is among the most widely used and versatile of digital musical interfaces. However, it lacks the ability to alter the pitch of a note after it has been played, a limitation which prevents the performer from executing common expressive techniques including vibrato and pitch bending. We present a system for controlling pitch from the keyboard surface using capacitive touch sensors to measure the locations of the player's fingers on the keys. The large community of trained pianists makes the keyboard a compelling target for augmentation, but it also poses a challenge: how can a musical interface be extended while making use of the existing techniques performers have spent thousands of hours learning? In this paper, user studies with conservatory pianists explore the constraints of traditional keyboard technique and evaluate the usability of the continuous pitch control system. The paper also discusses implications for the extension of other established interfaces in musical and non-musical contexts.

This paper introduces a technique for predicting harmonic sequences in a musical performance for which no score is available, using real-time audio signals. Recent short-term information is aligned with longer term information, contextualizing the present within the past, allowing predictions about the future of the performance to be made. Using a mid-level representation in the form of beat-synchronous harmonic sequences, we reduce the size of the information needed to represent the performance. This allows the implementation of real-time performance following in live performance situations. We conduct an objective evaluation on a database of rock, pop, and folk music. Our results show that we are able to predict a large majority of repeated harmonic content with no prior knowledge in the form of a score.

We present a technique for following a live performance in the situation where a score is not available. Making use of a local alignment between recent and longer term musical information, we place the present in the context of the past, allowing the prediction of future performance information. By representing music as sequences of beat-synchronous features we reduce the size of the information needed to represent the performance and allow performance following in real-time to occur.