Exploring recognition network representations for efficient speech inference on highly parallel platforms

The emergence of highly parallel computing platforms is enabling new trade-offs in algorithm design for automatic speech recognition. It naturally motivates the following investigation: do the most computationally efficient sequential algorithms lead to the most computationally efficient parallel algorithms? In this paper we explore two contending recognition network representations for speech inference engines: the linear lexical model (LLM) and the weighted finite state transducer (WFST). We demonstrate that while an inference engine using the simpler LLM representation evaluates 22

• Type: Journal
• Year: 2010
• Where: INTERSPEECH
• Authors: Jike Chong, Ekaterina Gonina, Kisun You, Kurt Keutzer
• Keywords: Inference Engine, INTERSPEECH 2010, LLM Representation, Signal Processing, Speech Inference Engine