Fixed-point Implementations of Speech Recognition Systems

Fixed-point hardware implementations of signal processing algorithms can often achieve higher performance with lower computational requirements than a floating-point implementation. However, the design of such systems is hard due to the difficulty of addressing the quantization issues. This paper presents an optimization approach to determining the wordlengths of fixed-point operators in a speech recognition system. This approach enables users to achieve the same result as in floating-point implementation with minimum hardware resources, resulting in reduced cost and perhaps lower power consumption. These techniques lead to an automated optimization based design methodology for fixedpoint based signal processing systems. An object oriented library, called Fixed, was developed to simulate fixed-point quantization effects. Quantization effects during recognition were analyzed, and appropriate wordlength that can balance hardware cost and calculation accuracy were determined for the operators.