A Low-resource, Miniature of the Etsi Distributed Speech R

The purpose of this work is to demonstrate that distributed speech recognition front-ends can be deployed in environments which providefor very little power and CPU resources, with possibly no degradation of speech recognition quality when compared to standard floatingpoint 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.