7th International Conference on Spoken Language Processing

September 16-20, 2002
Denver, Colorado, USA

A Low-Resource, Miniature Implementation of the ETSI Distributed Speech Recognition Front-End

Etienne Cornu, Hamid Sheikhzadeh, Robert Brennan

Dspfactory Ltd., Canada

The purpose of this work is to demonstrate that distributed speech recognition front-ends can be deployed in environments which provide for very little power and CPU resources, with possibly no degradation of speech recognition quality when compared to standard floating-point implementations. The ETSI distributed speech recognition front-end standard is implemented on an ultra low-power miniature DSP system. The efficient implementation of the ETSI algorithm components, i.e. feature extraction, feature compression and multi-framing, is accomplished through the use of three processing units running concurrently. In addition to a DSP core, an input/ output processor creates frames of input speech signals, and a weighted overlap-add (WOLA) filterbank unit performs windowing, FFT and vector multiplications. System evaluation using the TI digits database shows that the performance of the ultra low-power DSP system is equivalent to the reference implementation provided by ETSI.

Full Paper

Bibliographic reference.  Cornu, Etienne / Sheikhzadeh, Hamid / Brennan, Robert (2002): "A low-resource, miniature implementation of the ETSI distributed speech recognition front-end", In ICSLP-2002, 1581-1584.