In this paper, we present a new single sound source DOA estimation and tracking system based on the well-known SRP-PHAT algorithm and a three-dimensional Convolutional Neural Network. It uses SRP-PHAT power maps as input features of a fully convolutional causal architecture that uses 3D convolutional layers to accurately perform the tracking of a sound source even in highly reverberant scenarios where most of the state of the art techniques fail. Unlike previous methods, since we do not use bidirectional recurrent layers and all our convolutional layers are causal in the time dimension, our system is feasible for real-time applications and it provides a new DOA estimation for each new SRP-PHAT map. To train the model, we introduce a new procedure to simulate random trajectories as they are needed during the training, equivalent to an infinite-size dataset with high flexibility to modify its acoustical conditions such as the reverberation time. We use both acoustical simulations on a large range of reverberation times and the actual recordings of the LOCATA dataset to prove the robustness of our system and its good performance even using low-resolution SRP-PHAT maps.

In this paper, we present a new model for Direction of Arrival (DOA) estimation of sound sources based on an Icosahedral Convolutional Neural Network (CNN) applied over SRP-PHAT power maps computed from the signals received by a microphone array. This icosahedral CNN is equivariant to the 60 rotational symmetries of the icosahedron, which represent a good approximation of the continuous space of spherical rotations, and can be implemented using standard 2D convolutional layers, having a lower computational cost than most of the spherical CNNs. In addition, instead of using fully connected layers after the icosahedral convolutions, we propose a new soft-argmax function that can be seen as a differentiable version of the argmax function and allows us to solve the DOA estimation as a regression problem interpreting the output of the convolutional layers as a probability distribution. We prove that using models that fit the equivariances of the problem allows us to outperform other state-of-the-art models with a lower computational cost and more robustness, obtaining root mean square localization errors lower than $10^{\circ }$ even in scenarios with a reverberation time $\mathbf {T_{60}}$ of $1.5 \,\mathrm{s}$ .

The Steered Response Power with phase transform (SRP-PHAT) is one of the most employed techniques for Direction of Arrival (DOA) estimation with microphone arrays due its robustness against acoustical conditions as reverberation or noise. Among its main drawbacks is the growth of its computational complexity when the search space increases. To solve this issue, we propose the use of Neural Networks (NN) to obtain the DOA as a regression problem from a low resolution SRP-PHAT power map. The NNs can learn and exploit the information of the acoustic reflections of the room where the array is located with a training method that can be easily performed by an end user without technical knowledge.

Recent advancements in music source separation have significantly progressed, particularly in isolating vocals, drums, and bass elements from mixed tracks. These developments owe much to the creation and use of large-scale, multitrack datasets dedicated to these specific components. However, the challenge of extracting similarly sounding sources from orchestra recordings has not been extensively explored, largely due to a scarcity of comprehensive and clean (i.e bleed-free) multitrack datasets. In this paper, we introduce a novel multitrack dataset called SynthSOD, developed using a set of simulation techniques to create a realistic, musically motivated, and heterogeneous training set comprising different dynamics, natural tempo changes, styles, and conditions by employing high-quality digital libraries that define virtual instrument sounds for MIDI playback (a.k.a., soundfonts). Moreover, we demonstrate the application of a widely used baseline music separation model trained on our synthesized dataset w.r.t to the well-known EnsembleSet, and evaluate its performance under both synthetic and real-world conditions.