SEARCH SESSIONS

Search All
 
Refine Results:
 
Year(s)

SOCIAL MEDIA

EMAIL SUBSCRIPTION

 
 

GTC ON-DEMAND

Acoustics and Audio Processing
Presentation
Media
Exploring Recognition Network Representations for Efficient Speech Inference on the GPU
Speakers:
Jike Chong
Abstract:

We explore two contending recognition network representations for speech inference engines: the linear lexical model (LLM) and the weighted finite state transducer (WFST) on NVIDIA GTX285 and GTX480 GPUs. We demonstrate that while an inference engine using the simpler LLM representation evaluates 22x more transitions per second than the advanced WFST representation, the simple structure of the LLM representation allows 4.7-6.4x faster evaluation and 53-65x faster operands gathering for each state transition. We illustrate that the performance of a speech inference engine based on the LLM representation is competitive with the WFST representation on highly parallel GPUs.

 
Topics:
Acoustics and Audio Processing
Type:
Poster
Event:
GTC Silicon Valley
Year:
2010
Session ID:
P10C01
Download:
Share: