Low Power Speaker Identification using Look Up-free Gaussian Mixture Model in CMOS
Alberto Gianelli, Nick Iliev, Shamma Nasrin, Mariagrazia Graziano, Amit Ranjan Trivedi · 2019
This work discusses a CMOS-based implementation of low power speaker identification (SI) using Gaussian mixture models (GMMs). Conventionally, GMM-based SI relies on repeated access to log-add look-up table (LUT). With increasing dimensional of speaker models and/or number of speakers in the database, accesses to the LUT dominate the overall energy expense for SI. In this work, we discuss piece-wise linear approximations to GMM model that eliminate LUT accesses, thereby limiting model parameter storage in the register files alone, while incurring a minimal accuracy drop. We evaluate our scheme on TIMIT corpus where for text-independent SI and with a two-second test speech, our scheme achieves more than 90% accuracy across test-sets. We discuss the detailed architecture of the control unit, datapath, and key modules in our scheme. Compared to an equivalent design that requires LUT accesses in off -chip memories, our scheme limits power dissipation for SI to ~ 600 μW and consumes 4× less energy.