International Journal of Reconfigurable Computing / 2011 / Article / Tab 1

Research Article

FPGA Implementation of a Pipelined Gaussian Calculation for HMM-Based Large Vocabulary Speech Recognition

Table 1

Timing results for software implementation.

Frames/sSpeed (× real time)Percentage of Clock cycles spent on gaussian calc.

Sequential C++ 80%
C++ with SSE intrinsics 48%
8-thread parallel C++ with SSE 48%

Article of the Year Award: Outstanding research contributions of 2020, as selected by our Chief Editors. Read the winning articles.