Parallel Composition of Weighted Finite-State Transducers

Finite-state transducers (FSTs) are frequently used in speech recognition. Transducer composition is an essential operation for combining different sources of information at different granularities. However, composition is also one of the more computationally expensive operations. Due to the heterog...

Full description

Saved in:
Bibliographic Details
Main Authors: Sengupta, Shubho, Pratap, Vineel, Hannun, Awni
Format: Conference Proceeding
Language:English
Subjects:
Conferences
finite-state transducers
GPUs
Graphics processing units
Machine learning
parallel algorithms
Signal processing
Signal processing algorithms
Speech recognition
Transducers
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!