Close menu

SURE

Sunderland Repository records the research produced by the University of Sunderland including practice-based research and theses.

H-VECTORS: Improving the robustness in utterance-level speaker embeddings using a hierarchical attention model

Shi, Yanpei, Huang, Qiang and Hain, Thomas (2021) H-VECTORS: Improving the robustness in utterance-level speaker embeddings using a hierarchical attention model. Neural Networks, 142. pp. 329-339. ISSN 0893-6080

Item Type: Article

Abstract

In this paper, a hierarchical attention network is proposed to generate robust utterance-level embeddings (H-vectors) for speaker identification and verification. Since different parts of an utterance may have different contributions to speaker identities, the use of hierarchical structure aims to learn speaker related information locally and globally. In the proposed approach, frame-level encoder and attention are applied on segments of an input utterance and generate individual segment vectors. Then, segment level attention is applied on the segment vectors to construct an utterance representation. To evaluate the quality of the learned utterance-level speaker embeddings on speaker identification and verification, the proposed approach is tested on several benchmark datasets, such as the NIST SRE2008 Part1, the Switchboard Cellular (Part1), the CallHome American English Speech ,the Voxceleb1 and Voxceleb2 datasets. In comparison with some strong baselines, the obtained results show that the use of H-vectors can achieve better identification and verification performances in various acoustic conditions.

[img]
Preview
PDF
1-s2.0-S0893608021002203-main.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (1MB) | Preview

More Information

Uncontrolled Keywords: Speaker embeddings, Hierarchical attention, Speaker identification, Speaker verification, Attention mechanism
Depositing User: Qiang Huang

Identifiers

Item ID: 16097
Identification Number: https://doi.org/10.1016/j.neunet.2021.05.024
ISSN: 0893-6080
URI: http://sure.sunderland.ac.uk/id/eprint/16097
Official URL: https://www.sciencedirect.com/science/article/pii/...

Users with ORCIDS

ORCID for Yanpei Shi: ORCID iD orcid.org/0000-0001-8157-2630
ORCID for Qiang Huang: ORCID iD orcid.org/0000-0002-2943-2283
ORCID for Thomas Hain: ORCID iD orcid.org/0000-0003-0939-3464

Catalogue record

Date Deposited: 22 May 2023 11:31
Last Modified: 11 Jul 2023 08:01

Contributors

Author: Yanpei Shi ORCID iD
Author: Qiang Huang ORCID iD
Author: Thomas Hain ORCID iD

University Divisions

Faculty of Technology > School of Computer Science

Subjects

Computing > Artificial Intelligence
Computing > Human-Computer Interaction

Actions (login required)

View Item (Repository Staff Only) View Item (Repository Staff Only)