PROJECT TITLE :
Memory-efficient buffering method and enhanced reference template for embedded automatic speech recognition system
This work realises a memory-economical embedded automatic speech recognition (ASR) system on a resource-constrained platform. A buffering methodology referred to as ultra-low queue-accumulator buffering is presented to efficiently use the constrained memory to extract the linear prediction cepstral coefficient (LPCC) feature in the embedded ASR system. The optimal order of the LPCC is evaluated to balance the popularity accuracy and the computational value. In the decoding part, the proposed enhanced cross-words reference templates (CWRTs) method is incorporated into the template matching methodology to succeed in the speaker-independent characteristic of ASR tasks without the large memory burden of the traditional CWRTs method. The proposed techniques are implemented on a 16-bit microprocessor GPCE063A platform with a forty nine.152 MHz clock, employing a sampling rate of eight kHz. Experimental results demonstrate that recognition accuracy reaches ninety five.twenty twop.c in a thirty-sentence speaker-independent embedded ASR task, using only 0.75 kB RAM.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here