Attention-Based Models for Text-Dependent Speaker Verification

TL;DR

This paper investigates the application of attention mechanisms in end-to-end text-dependent speaker verification, demonstrating that attention improves system accuracy by effectively summarizing relevant speech features.

Contribution

It introduces and compares various attention layer topologies and pooling methods, showing their effectiveness in enhancing speaker verification performance.

Findings

Attention models reduce EER by 14% over baseline

Different attention topologies and pooling methods are evaluated

Attention mechanisms improve sequence summarization in speaker verification

Abstract

Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands through the entire length of an input sequence. In this paper, we analyze the usage of attention mechanisms to the problem of sequence summarization in our end-to-end text-dependent speaker recognition system. We explore different topologies and their variants of the attention layer, and compare different pooling methods on the attention weights. Ultimately, we show that attention-based models can improves the Equal Error Rate (EER) of our speaker verification system by relatively 14% compared to our non-attention LSTM baseline model.