Attention-Based Models for Text-Dependent Speaker Verification (2017-10-28T00:00:00.000000Z)

TL;DR

This paper analyzes the usage of attention mechanisms to the problem of sequence summarization in the authors' end-to-end text-dependent speaker recognition system and shows that attention-based models can improves the Equal Error Rate (EER) of the speaker verification system by relatively 14% compared to their non-attention LSTM baseline model.

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.

Authors

Quan Wang

9 papers

Li Wan

5 papers

I. López-Moreno

7 papers

Attention-Based Models for Text-Dependent Speaker Verification

TL;DR

Abstract

Authors

References18 items

Front-End Factor Analysis For Speaker Verification

Generalized End-to-End Loss for Speaker Verification

Speaker Diarization with LSTM

End-to-End DNN Based Speaker Recognition Inspired by I-Vector and PLDA

End-to-end text-dependent speaker verification

Effective Approaches to Attention-based Neural Machine Translation

Attention-Based Models for Speech Recognition

Automatic gain control and multi-style training for robust small-footprint keyword spotting with deep neural networks

FaceNet: A unified embedding for face recognition and clustering

Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

Small-footprint keyword spotting using deep neural networks

Front-End Factor Analysis for Speaker Verification

Long Short-Term Memory

Deep Learning

Long short-term memory recurrent neural network architectures for large scale acoustic modeling

Analysis of i-vector Length Normalization in Speaker Recognition Systems

Tomato, tomahto. google home now supports multiple users

Voice match will allow google home to recognize your voice

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names