GPU-based approaches for real-time sound source localization using the SRP-PHAT algorithm

Authors:
Vicente Peruffo Minotto;Claudio Rosito Jung;Luiz Gonzaga Da Silveira;Bowon Lee
Affiliations:
Instituto de Informática, Universidade Federal do Rio Grande do Sul, RS, Brazil;Instituto de Informática, Universidade Federal do Rio Grande do Sul, RS, Brazil;Applied Computing Graduate Program (PIPCA), Universidade do Vale do Rio dos Sinos, RS, Brazil;Mobile and Immersive Experience Lab, Hewlett-Packard Laboratories, Palo Alto, CA, USA
Venue:
International Journal of High Performance Computing Applications
Year:
2013

Citing 7
Cited 0

Spoken Dialogues with Computers

Spoken Dialogues with Computers
Using OpenMP: Portable Shared Memory Parallel Programming (Scientific and Engineering Computation)

Using OpenMP: Portable Shared Memory Parallel Programming (Scientific and Engineering Computation)
NVIDIA Tesla: A Unified Graphics and Computing Architecture

IEEE Micro
High performance discrete Fourier transforms on graphics processors

Proceedings of the 2008 ACM/IEEE conference on Supercomputing
Fast tridiagonal solvers on the GPU

Proceedings of the 15th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming
Programming Massively Parallel Processors: A Hands-on Approach

Programming Massively Parallel Processors: A Hands-on Approach
Robust user context analysis for multimodal interfaces

ICMI '11 Proceedings of the 13th international conference on multimodal interfaces

Quantified Score

Hi-index	0.00

Visualization

Abstract

The aim of most microphone array applications is to localize sound sources in a noisy and reverberant environment. For that purpose, many different sound source localization (SSL) algorithms have been proposed, where the SRP-PHAT (steered response power using the phase transform) has been known as one of the state-of-the-art methods. Its original formulation allows two different practical implementations, one that is computed in the frequency domain (FDSP) and another in the time domain (TDSP), which can be enhanced by interpolation. However, the main problem of this algorithm is its high computational cost due to intensive grid scan in search for the sound source. Considering the power of graphics processing units (GPUs) for working with massively parallelizable compute-intensive algorithms, we present two highly scalable GPU-based versions of the SRP-PHAT, one for each formulation, and also an implementation of the cubic splines interpolation in the GPU. These approaches exploit the parallel aspects of the SRP-PHAT, allowing real-time execution for large search grids. Comparing our GPU approaches against traditional multithreaded CPU approaches, results show a speed up of 275脙聴 for the FDSP, and 70脙聴 for the TDSP with interpolation, when comparing high-end GPUs with high-end CPUs.