no code implementations • 27 Sep 2023 • Zihao Deng, Benjamin Ghaemmaghami, Ashish Kumar Singh, Benjamin Cho, Leo Orshansky, Mattan Erez, Michael Orshansky
At constant model quality, MLET allows embedding dimension, and model size, reduction by up to 16x, and 5. 8x on average, across the models.
no code implementations • 10 Jun 2020 • Benjamin Ghaemmaghami, Zihao Deng, Benjamin Cho, Leo Orshansky, Ashish Kumar Singh, Mattan Erez, Michael Orshansky
Increasing the dimension of embedding vectors improves model accuracy but comes at a high cost to model size.
no code implementations • Conference 2019 • Shikha Dubey, Ashish Kumar Singh, Manoj Kumar Singh
During the acquisition of the speech signal by the non-contact Speech Sensor (SS), the signal is degraded by severe colored noises which are non-linear and non-uniform in nature.