FPGA-based Acceleration for Tracking Audio Effects in Movies

Abstract

In this paper we propose an FPGA-based hardware platform to accelerate an audio tracking method. Our tracking approach is inspired by the problem of molecular sequence alignment and adopts a well-known dynamic programming algorithm (Smith-Waterman algorithm) from the area of bioinformatics. However, the high computational complexity of such algorithms imposes a significant barrier to their adoption by audio tracking systems. To alleviate the time-consuming problem and achieve realistic response times, we propose the acceleration of computationally intensive parts of our tracking method using an FPGA-based platform. Our FPGA accelerator is actually based on the systolization of the Smith-Waterman algorithm proposed in previous approaches for the acceleration of bio-sequence scanning but the special requirements of the audio tracking method impose significant design challenges in the accelerator architecture. The accelerator has been implemented in a Xilinx Virtex-5 device and the experimental results show that it achieves significant speedup compared with the software implementation of the tracking method. The proposed approach has been tested in the context of detecting animal sounds in audio streams from movies, where a basic requirement is to reduce the noisiness of the detection results by means of exploiting the statistical nature of the scores that are generated by the dynamic programming algorithm.