Parallel scalability in speech recognition: Inference engines in large vocabulary continuous speech recognition

Kisun You, Jike Chong, Youngmin Yi, Ekaterina Gonina, Christopher J. Hughes, Yen Kuang Chen, Wonyong Sung, Kurt Keutzer

Research output: Contribution to journalArticlepeer-review

47 Scopus citations

Abstract

Parallel scalability allows an application to efficiently utilize an increasing number of processing elements. In this article, we explore a design space for parallel scalability for an inference engine in large vocabulary continuous speech recognition (LVCSR). Our implementation of the inference engine involves a parallel graph traversal through an irregular graph-based knowledge network with millions of states and arcs. The challenge is not only to define a software architecture that exposes sufficient fine-grained application concurrency but also to efficiently synchronize between an increasing number of concurrent tasks and to effectively utilize parallelism opportunities in today's highly parallel processors.

Original languageEnglish
Pages (from-to)124-135
Number of pages12
JournalIEEE Signal Processing Magazine
Volume26
Issue number6
DOIs
StatePublished - 2009

Keywords

  • Algorithm design and analysis
  • Program processors
  • Signal processing algorithms
  • Speech recognition
  • Synchronization

Fingerprint

Dive into the research topics of 'Parallel scalability in speech recognition: Inference engines in large vocabulary continuous speech recognition'. Together they form a unique fingerprint.

Cite this