11th Annual Conference of the International Speech Communication Association

Makuhari, Chiba, Japan
September 26-30. 2010

Parallel Lexical-Tree Based LVCSR on Multi-Core Processors

Naveen Parihar (1), Ralf Schlüter (2), David Rybach (2), Eric A. Hansen (1)

(1) Mississippi State University, USA
(2) RWTH Aachen University, Germany

Exploiting the computational power of multi-core processors for large vocabulary continuous speech recognition (LVCSR) requires changes in the recognizer architecture. In this paper, we consider how to parallelize the search component of a lexical-tree based speech recognizer. We introduce a hybrid-parallel method for dynamically dividing the lexical-tree copies among the cores at each frame. Each core is responsible for graph traversal in the lexical-tree copies allocated to it. This approach is compared to a previously-introduced static method that divides the lexical tree itself, so that each core is responsible for a different subtree of each of the lexical-tree copies. The new method outperforms the previous one when applied to the RWTH TC-STAR EPPS English LVCSR system running on four cores of an Intel Core-i7 processor with varying pruning-beam width settings.

Full Paper

Bibliographic reference.  Parihar, Naveen / Schlüter, Ralf / Rybach, David / Hansen, Eric A. (2010): "Parallel lexical-tree based LVCSR on multi-core processors", In INTERSPEECH-2010, 1485-1488.