Modern smart glasses leverage advanced audio sensing and machine learnin...
Wake word detection exists in most intelligent homes and portable device...
This paper proposes a hardware-efficient architecture, Linearized Convol...
Training speaker-discriminative and robust speaker verification systems
...
Structural analysis is a method for verifying equation-oriented models i...
Google's multilingual speech recognition system combines low-level acous...
In this paper, we propose "personal VAD", a system to detect the voice
a...
In many scenarios of a language identification task, the user will speci...
We present a novel algorithm, called Links, designed to perform online
c...
Attention-based models have recently shown great performance on a range ...
For many years, i-vector based speaker embedding techniques were the dom...
In this paper, we propose a new loss function called generalized end-to-...
Deformable Parts Models and Convolutional Networks each have achieved no...