Memory Layers with Multi-Head Attention Mechanisms for Text-Dependent Speaker Verification

In this paper, we explore an approach based on memory layers and multi-head attention mechanisms to improve in an efficient way the performance of text-dependent speaker verification (SV) systems. The most extended SV systems based on Deep Neural Networks (DNN) extract the embedding of the utterance...

Full description

Saved in:
Bibliographic Details
Published inICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 6154 - 6158
Main Authors Mingote, Victoria, Miguel, Antonio, Ortega, Alfonso, Lleida, Eduardo
Format Conference Proceeding
LanguageEnglish
Published IEEE 06.06.2021
Subjects
Deep architecture
Knowledge engineering
Memory Layer
Memory management
Multi-head Attention
Neural networks
Phonetics
Temporal Attention
Text-Dependent Speaker Verification
Training
Online AccessGet full text

Cover

More Information
Summary:In this paper, we explore an approach based on memory layers and multi-head attention mechanisms to improve in an efficient way the performance of text-dependent speaker verification (SV) systems. The most extended SV systems based on Deep Neural Networks (DNN) extract the embedding of the utterance from the average pooling of the temporal dimension after processing. Unlike previous works, we can exploit the phonetic knowledge needed for text-dependent SV systems by combining the temporal attention of multiple parallel heads with the phonetic embeddings extracted from a phonetic classification network, which helps to guide to the attention mechanism with the role of the positional embedding. The addition of a memory layer to a text-dependent SV system was tested on the RSR2015-part II and DeepMine-part I databases, where, in both cases outperformed the baseline result and the reference system based on the same transformer network without the memory layer.
ISSN:2379-190X
DOI:10.1109/ICASSP39728.2021.9414859