Self-attention is a useful mechanism to build generative models for language and images. It
determines the importance of context elements by comparing each element to the current …

In this paper, we propose a new loss function called generalized end-to-end (GE2E) loss,
which makes the training of speaker verification models more efficient than our previous …

For many years, i-vector based audio embedding techniques were the dominant approach
for speaker verification and speaker diarization applications. However, mirroring the rise of …

In this paper we present a data-driven, integrated approach to speaker verification, which
maps a test utterance and a few reference utterances directly to a single score for verification …

Speaker identification is a classification task which aims to identify a subject from a given
time-series sequential data. Since the speech signal is a continuous one-dimensional time …

We describe a large vocabulary speech recognition system that is accurate, has low latency,
and yet has a small enough memory and computational footprint to run faster than real-time …

Robust and far-field speech recognition is critical to enable true hands-free communication.
In far-field conditions, signals are attenuated due to distance. To improve robustness to …

For the challenging semantic image segmentation task the most efficient models have
traditionally combined the structured modelling capabilities of Conditional Random Fields …

With the popularity of intelligent audio systems in recent years, their vulnerabilities have
become an increasing public concern. Existing studies have designed a set of machine …

In classical cosmological analysis of large-scale structure surveys with two-point functions,
the parameter measurement precision is limited by several key degeneracies within the …