Publications
Detail of publication
Citation
p. 450-454, IEEE Print, Danvers, USA, 2014. : An Open-Source GPU-Accelerated Feature Extraction Tool . 12th International Conference on Signal Processing - ICSP2014, 12th International Conference on Signal Processing - ICSP2014,
Download PDF
Abstract
An extraction of feature-vectors from speech audio signal is a computationally intensive task. However, MFCC and PLP features remain the most popular for more than a decade. We made a GPU-accelerated implementation of the feature extraction processing. The implementation produces identical features as the reference Hidden Markov Toolkit (HTK) but in a fraction of the elapsed time. The saved time can be invested elsewhere and thus it can speed-up research. The implementation was developed in CUDA which supports NVidia GPUs only. So, we added an Open-CL implementation to support any current GPU. The project is an open-source package, thus research community can modify or adapt the implementation to their needs.
Detail of publication
Title: | An Open-Source GPU-Accelerated Feature Extraction Tool |
---|---|
Author: | Michálek J. ; Vaněk J. |
Language: | English |
Year: | 2014 |
Type of publication: | Papers in proceedings of reviewed conferences |
Book title: | 12th International Conference on Signal Processing - ICSP2014 |
Title of journal or book: | 12th International Conference on Signal Processing - ICSP2014 |
Page: | 450 - 454 |
ISBN: | 978‐1‐4799‐2187‐4 |
Publisher: | IEEE Print |
Address: | Danvers, USA |
Keywords
GPU, CUDA, OpenCL, MFC, PLP, feature processing, speech, HTK
BibTeX
@INPROCEEDINGS{MichalekJ_2014_AnOpen-Source, author = {Mich\'{a}lek J. and Van\v{e}k J.}, title = {An Open-Source GPU-Accelerated Feature Extraction Tool}, year = {2014}, publisher = {IEEE Print}, journal = {12th International Conference on Signal Processing - ICSP2014}, address = {Danvers, USA}, pages = {450-454}, booktitle = {12th International Conference on Signal Processing - ICSP2014}, ISBN = {978-1-4799-2187-4}, url = {http://www.kky.zcu.cz/en/publications/MichalekJ_2014_AnOpen-Source}, }