GPU-Accelerated Forward-Backward Algorithm with Application to Lattice-Free MMI
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F22%3APU144936" target="_blank" >RIV/00216305:26230/22:PU144936 - isvavai.cz</a>
Result on the web
<a href="https://ieeexplore.ieee.org/document/9746824" target="_blank" >https://ieeexplore.ieee.org/document/9746824</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICASSP43922.2022.9746824" target="_blank" >10.1109/ICASSP43922.2022.9746824</a>
Alternative languages
Result language
angličtina
Original language name
GPU-Accelerated Forward-Backward Algorithm with Application to Lattice-Free MMI
Original language description
We propose to express the forward-backward algorithm in terms of operations between sparse matrices in a specific semiring. This new perspective naturally leads to a GPU-friendly algorithm which is easy to implement in Julia or any programming languages with native support of semiring algebra. We use this new implementation to train a TDNN with the LF-MMI objective function and we compare the training time of our system with PyChaina recently introduced C++/CUDA implementation of the LF-MMI loss. Our implementation is about two times faster while not having to use any approximation such as the "leaky-HMM".
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISBN
978-1-6654-0540-9
ISSN
—
e-ISSN
—
Number of pages
5
Pages from-to
8417-8421
Publisher name
IEEE Signal Processing Society
Place of publication
Singapore
Event location
Singapore
Event date
May 22, 2022
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000864187908145