Noise Invariant Frame Selection: A Simple Method to Address the Background Noise Problem for Text-independent Speaker Verification

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

Abstract

The performance of speaker-related systems usually degrades heavily in practical applications largely due to the presence of 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 verification systems achieves similar performance when we change the constraints (hyper-parameters) or features, which indicates that it is robust and easy to reproduce. Since NIFS is designed as a general algorithm, it could be further applied to other similar tasks.

Citation

Song, S., Zhang, S., Schuller, B. W., Shen, L., & Valstar, M. (2018, July). Noise Invariant Frame Selection: A Simple Method to Address the Background Noise Problem for Text-independent Speaker Verification. Presented at International Joint Conference on Neural Networks 2018, Rio de Janeiro, Brazil

• Presentation Conference Type: Edited Proceedings
• Conference Name: International Joint Conference on Neural Networks 2018
• Start Date: Jul 8, 2018
• End Date: Jul 13, 2018
• Acceptance Date: Mar 15, 2018
• Online Publication Date: Oct 14, 2018
• Publication Date: 2018
• Deposit Date: Apr 30, 2018
• Publicly Available Date: Oct 14, 2018
• Peer Reviewed: Peer Reviewed
• Series ISSN: 2161-4407
• Book Title: Proceedings of the 2018 International Joint Conference on Neural Networks (IJCNN)
• ISBN: 978-1-5090-6015-3
• DOI: https://doi.org/10.1109/IJCNN.2018.8489497
• Public URL: https://nottingham-repository.worktribe.com/output/945806
• Publisher URL: https://ieeexplore.ieee.org/document/8489497
• Related Public URLs: http://www.ecomp.poli.br/~wcci2018/
• 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.
• Contract Date: Apr 30, 2018