Publication detail

GPU-Accelerated Forward-Backward Algorithm with Application to Lattice-Free MMI

ONDEL YANG, L. LAM-YEE-MUI, L. KOCOUR, M. CORRO, C. BURGET, L.

Original Title

GPU-Accelerated Forward-Backward Algorithm with Application to Lattice-Free MMI

Type

conference paper

Language

English

Original Abstract

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".

Keywords

Lattice-Free MMI, end-to-end ASR, Julia language, forward-backward

Authors

ONDEL YANG, L.; LAM-YEE-MUI, L.; KOCOUR, M.; CORRO, C.; BURGET, L.

Released

27. 5. 2022

Publisher

IEEE Signal Processing Society

Location

Singapore

ISBN

978-1-6654-0540-9

Book

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Pages from

8417

Pages to

8421

Pages count

5

URL

https://ieeexplore.ieee.org/document/9746824

BibTex

@inproceedings{BUT178409,
  author="Lucas Antoine Francois {Ondel} and L'ea-Marie {Lam-Yee-Mui} and Martin {Kocour} and Caio Filippo {Corro} and Lukáš {Burget}",
  title="GPU-Accelerated Forward-Backward Algorithm with Application to Lattice-Free MMI",
  booktitle="ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
  year="2022",
  pages="8417--8421",
  publisher="IEEE Signal Processing Society",
  address="Singapore",
  doi="10.1109/ICASSP43922.2022.9746824",
  isbn="978-1-6654-0540-9",
  url="https://ieeexplore.ieee.org/document/9746824"
}