Scalable HMM based inference engine in large vocabulary continuous speech recognition

Parallel scalability allows an application to efficiently utilize an increasing number of processing elements. In this paper 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 graphbased 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. We propose four application-level implementation alternatives we call "algorithm styles" and construct highly optimized implementations on two parallel platforms: an Intel Core i7 multicore processor and a NVIDIA GTX280 manycore processor. The highest performing ...

• Type: Journal
• Year: 2009
• Where: ICMCS
• Authors: Jike Chong, Kisun You, Youngmin Yi, Ekaterina Gonina, Christopher Hughes, Wonyong Sung, Kurt Keutzer
• Keywords: Core I7, ICMCS 2009, Inference Engine, Multimedia, Parallel Scalability