What are you looking for today?

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

Document

Abstract

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.

Item Type: Article
Uncontrolled Keywords: Speaker embeddings, Hierarchical attention, Speaker identification, Speaker verification, Attention mechanism
Depositing User: Qiang Huang
URI: https://sure.sunderland.ac.uk/id/eprint/16097

Further Details

More Information

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

Identifiers

Item ID
16097
Identification Number
ISSN
0893-6080

Users with ORCIDS

ORCID for Yanpei Shi
ORCID for Qiang Huang
ORCID for Thomas Hain

Catalogue record

Date Deposited
22 May 2023 11:31
Last Modified
04 Jun 2025 14:58

Actions (login required)

View Item (Repository Staff Only)

Downloads per month over past year