Optimization of Weighted Finite State Transducer for Speech Recognition

Louis-Marie Aubert, Roger Woods, Scott Fischaber, Richard Veitch

Research output: Contribution to journalArticle

1 Citation (Scopus)
37 Downloads (Pure)

Abstract

There is considerable interest in creating embedded, speech recognition hardware using the weighted finite state transducer (WFST) technique but there are performance and memory usage challenges. Two system optimization techniques are presented to address this; one approach improves token propagation by removing the WFST epsilon input arcs; another one-pass, adaptive pruning algorithm gives a dramatic reduction in active nodes to be computed. Results for memory and bandwidth are given for a 5,000 word vocabulary giving a better practical performance than conventional WFST; this is then exploited in an adaptive pruning algorithm that reduces the active nodes from 30,000 down to 4,000 with only a 2 percent sacrifice in speech recognition accuracy; these optimizations lead to a more simplified design with deterministic performance.
Original languageEnglish
Pages (from-to)1607-1615
Number of pages9
JournalIEEE Transactions on Computers
Volume62
Issue number8
DOIs
Publication statusPublished - Aug 2013

Keywords

  • Embedded processors
  • WFST
  • Memory organization
  • speech recognition

Fingerprint Dive into the research topics of 'Optimization of Weighted Finite State Transducer for Speech Recognition'. Together they form a unique fingerprint.

  • Cite this