Last: Scalable Lattice-Based Speech Modelling in Jax

We introduce LAST, a LAttice-based Speech Transducer library in JAX. With an emphasis on flexibility, ease-of-use, and scalability, LAST implements differentiable weighted finite state automaton (WFSA) algorithms needed for training & inference that scale to a large WFSA such as a recognition la...

Full description

Saved in:
Bibliographic Details
Main Authors: Wu, Ke, Variani, Ehsan, Bagby, Tom, Riley, Michael
Format: Conference Proceeding
Language:English
Subjects:
ASR
Automata
Benchmark testing
Scalability
Signal processing
Signal processing algorithms
Training
Transducers
weighted finite state machines
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We introduce LAST, a LAttice-based Speech Transducer library in JAX. With an emphasis on flexibility, ease-of-use, and scalability, LAST implements differentiable weighted finite state automaton (WFSA) algorithms needed for training & inference that scale to a large WFSA such as a recognition lattice over the entire utterance. Despite these WFSA algorithms being well-known in the literature, new challenges arise from performance characteristics of modern architectures, and from nuances in automatic differentiation. We describe a suite of generally applicable techniques employed in LAST to address these challenges, and demonstrate their effectiveness with benchmarks on TPUv3 and V100 GPU.
ISSN:2379-190X
DOI:10.1109/ICASSP49357.2023.10095774