MSP432 Speech Recognition Power

Leo,
I found the following statements in the release notes:

Processing Cycles
Processor cycle requirements are a complex function of the trained models, the input speech data and background noise, and the quality of the match between the trained data and the input speech. As a general rule, when there is less background noise and the input speech matches a model well, then cycle usage decreases during active recognition search. When there is no speech and background noise is low or at a moderate level and not changing appreciably, MinHMM will assume the signal is in a background noise condition and enter a background processing mode. When speech is present, or when other background noises are appreciable and varying, then MinHMM will enter the active recognition search mode to attempt to match the audio signal to a model, thus causing higher cycle usage. The table below provides estimates of typical cycle usage measured while running the MinHMM example demo program on the MSP432P401R operating at a clock rate of 48MHz . Due to variations in models, background noise, audio quality, and other factors the actual cycles an application requires may differ from these estimates.

Condition Average MCPS Maximum MCPS
(% of Available Cycles) (% of Available Cycles)
Background Mode 2 (4.3%) 2 (4.3%)

Active Search Mode 6.2(13%) 7.7 (16%)
(1 model)

Active Search Mode 17.3 (36%) 22.1 (46%)
(5 models)


Power Consumption
The MinHMM speech recognizer consumes arrays of sampled audio data. Typically the arrays consist of 160 samples collected at an 8kHz sample rate, so an array of data is provided to MinHMM each 20ms. The power needed to process these arrays is based on the cycles required for processing the data arrays, which was discussed in the prior paragraph. The total power consumption of an application will in addition depend heavily on hardware and application design. For lowest power operation the design should utilize low-power best practices. The hardware should use low-power components for audio collection, such as the microphone and pre-amplifier. The application should shut down peripherals during periods when they are not being used and use the lowest clocking rates necessary. Application software should utilize the low-power modes of the processor, such as LPM3, during idle times. Excluding the external hardware, estimates of processor power consumption for an application utilizing these practices ranges from 250µA in background mode to 1.8mA in active search mode with five models active.

The current MinHMM example program demonstrates the use of the MinHMM speech recognizer, but for simplicity of illustration it was not designed for lowest power operation. For example, during idle times it uses LPM0 and the 48MHz clock remains running.

Regards,
Chris