Audio information retrieval (AIR) is a field with potential applications in automatic annotation, music recommendation, as well as music tutoring and accuracy verification systems. Extracting the raga, or melodic style, of improvisational Hindustani Classical music is a challenging problem in AIR due to the music’s melodic variation and inconsistent temporal spacing. In this work, a hierarchical deep learning system, PhonoNet, is proposed for extracting information from audio data with temporal variation. PhonoNet is applied to a comprehensive Hindustani Classical music dataset and achieves a new state-of-the-art 98.9% accuracy in raga prediction.

Autonomous driving requires operation in different behavioral modes ranging from lane following and intersection crossing to turning and stopping. However, most existing deep learning approaches to autonomous driving do not consider the behavioral mode in the training strategy. This paper describes a technique for learning multiple distinct behavioral modes in a single deep neural network through the use of multi-modal multi-task learning. We study the effectiveness of this approach, denoted MultiNet, using self-driving model cars for driving in unstructured environments such as sidewalks and unpaved roads. Using labeled data from over one hundred hours of driving our fleet of 1/10th scale model cars, we trained different neural networks to predict the steering angle and driving speed of the vehicle in different behavioral modes. We show that in each case, MultiNet networks outperform networks trained on individual modes while using a fraction of the total number of parameters.