The Fixed-Point Optimization of Mel Frequency Cepstrum Coefficients for Speech Recognition
Speech recognition is a computationally complexity process and it is suitable for battery powered devices like mobile phones and other personal PDAs. Particularly the parts of mel-scaled frequency cepstrum coefficients (MFCCs) are a process of dimension reduction for reducing resources to accurately describe speech samples. The optimized algorithm was applied to a binary-search-based lookup table to take place of original Taylor expansion algorithm, and it reduced the time of execution frames to meet real-time speech recognition system. The look-up tables were established by analysing the pseudo code to reduce the memory size in this paper. The transition algorithm of floating-point MFCCs to fixed-point ones was investigated to reach a higher precision in the first order approximation of linear interpolation of Log algorithm. The Hidden Markov Model Toolke (HTK) was applied to training the speech samples of Texas Instruments and Massachusetts Institute of Technology (TIM IT). The rate of speech recognition improved 12.02V* by the optimized algorithm in the system of speech recognition.
MFCCs HTK look-up table fixed-point TIMIT
Ge Zhang Jinghua Yin Qian Liu Chao Yang
School of Applied Sciences,Harbin University of Science and Technology Harbin,China
国际会议
The 6th International Forum on Strategic Technology(IFOST 2011)(第六届国际战略技术论坛)
哈尔滨
英文
1172-1175
2011-08-22（万方平台首次上网日期，不代表论文的发表时间）