Skip to main content

Research Repository

Advanced Search

Noise invariant frame selection: a simple method to address the background noise problem for text-independent speaker verification

Song, Siyang; Shuimei, Zhang; Schuller, Björn; Shen, Linlin; Valstar, Michel F.

Authors

Siyang Song Siyang.Song@nottingham.ac.uk

Zhang Shuimei

Björn Schuller

Linlin Shen



Abstract

The performance of speaker-related systems usually degrades heavily in practical applications largely due to the background noise. To improve the robustness of such systems in unknown noisy environments, this paper proposes a simple pre-processing method called Noise Invariant Frame Selection (NIFS). Based on several noisy constraints, it selects noise invariant frames from utterances to represent speakers. Experiments conducted on the TIMIT database showed that the NIFS can significantly improve the performance of Vector Quantization (VQ), Gaussian Mixture Model-Universal Background Model (GMM-UBM) and i-vector-based speaker verification systems in different unknown noisy environments with different SNRs, in comparison to their baselines. Meanwhile, the proposed NIFS-based speaker systems has achieves similar performance when we change the constraints (hyper-parameters) or features, which indicates that it is easy to reproduce. Since NIFS is designed as a general algorithm, it could be further applied to other similar tasks.

Start Date Jul 8, 2018
Publication Date Oct 15, 2018
Peer Reviewed Peer Reviewed
Book Title 2018 International Joint Conference on Neural Networks (IJCNN)
ISBN 978-1-5090-6014-6
APA6 Citation Song, S., Shuimei, Z., Schuller, B., Shen, L., & Valstar, M. F. (2018). Noise invariant frame selection: a simple method to address the background noise problem for text-independent speaker verification. In 2018 International Joint Conference on Neural Networks (IJCNN). https://doi.org/10.1109/IJCNN.2018.8489497
DOI https://doi.org/10.1109/IJCNN.2018.8489497
Publisher URL https://ieeexplore.ieee.org/document/8489497
Related Public URLs http://www.ecomp.poli.br/~wcci2018/
Copyright Statement Copyright information regarding this work can be found at the following address: http://eprints.nottingh.../end_user_agreement.pdf
Additional Information © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Files

noise-invariant-frame.pdf (413 Kb)
PDF

Copyright Statement
Copyright information regarding this work can be found at the following address: http://eprints.nottingham.ac.uk/end_user_agreement.pdf





You might also like



Downloadable Citations

;