ParaNoise-SV: Integrated Approach for Noise-Robust Speaker Verification with Parallel Joint Learning of Speech Enhancement and Noise Extraction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Minu, Jang, Kangwook, Kim, Hoirin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916890370113536
author Kim, Minu
Jang, Kangwook
Kim, Hoirin
author_facet Kim, Minu
Jang, Kangwook
Kim, Hoirin
contents Noise-robust speaker verification leverages joint learning of speech enhancement (SE) and speaker verification (SV) to improve robustness. However, prevailing approaches rely on implicit noise suppression, which struggles to separate noise from speaker characteristics as they do not explicitly distinguish noise from speech during training. Although integrating SE and SV helps, it remains limited in handling noise effectively. Meanwhile, recent SE studies suggest that explicitly modeling noise, rather than merely suppressing it, enhances noise resilience. Reflecting this, we propose ParaNoise-SV, with dual U-Nets combining a noise extraction (NE) network and a speech enhancement (SE) network. The NE U-Net explicitly models noise, while the SE U-Net refines speech with guidance from NE through parallel connections, preserving speaker-relevant features. Experimental results show that ParaNoise-SV achieves a relatively 8.4% lower equal error rate (EER) than previous joint SE-SV models.
format Preprint
id arxiv_https___arxiv_org_abs_2508_07219
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ParaNoise-SV: Integrated Approach for Noise-Robust Speaker Verification with Parallel Joint Learning of Speech Enhancement and Noise Extraction
Kim, Minu
Jang, Kangwook
Kim, Hoirin
Audio and Speech Processing
Sound
I.2.7; H.5.5; I.5.4
Noise-robust speaker verification leverages joint learning of speech enhancement (SE) and speaker verification (SV) to improve robustness. However, prevailing approaches rely on implicit noise suppression, which struggles to separate noise from speaker characteristics as they do not explicitly distinguish noise from speech during training. Although integrating SE and SV helps, it remains limited in handling noise effectively. Meanwhile, recent SE studies suggest that explicitly modeling noise, rather than merely suppressing it, enhances noise resilience. Reflecting this, we propose ParaNoise-SV, with dual U-Nets combining a noise extraction (NE) network and a speech enhancement (SE) network. The NE U-Net explicitly models noise, while the SE U-Net refines speech with guidance from NE through parallel connections, preserving speaker-relevant features. Experimental results show that ParaNoise-SV achieves a relatively 8.4% lower equal error rate (EER) than previous joint SE-SV models.
title ParaNoise-SV: Integrated Approach for Noise-Robust Speaker Verification with Parallel Joint Learning of Speech Enhancement and Noise Extraction
topic Audio and Speech Processing
Sound
I.2.7; H.5.5; I.5.4
url https://arxiv.org/abs/2508.07219