Towards single integrated spoofing-aware speaker verification embeddings
- URL: http://arxiv.org/abs/2305.19051v2
- Date: Thu, 1 Jun 2023 11:18:36 GMT
- Title: Towards single integrated spoofing-aware speaker verification embeddings
- Authors: Sung Hwan Mun, Hye-jin Shim, Hemlata Tak, Xin Wang, Xuechen Liu, Md
Sahidullah, Myeonghun Jeong, Min Hyun Han, Massimiliano Todisco, Kong Aik
Lee, Junichi Yamagishi, Nicholas Evans, Tomi Kinnunen, Nam Soo Kim, and
Jee-weon Jung
- Abstract summary: This study aims to develop a single integrated spoofing-aware speaker verification embeddings.
We analyze that the inferior performance of single SASV embeddings comes from insufficient amount of training data.
Experiments show dramatic improvements, achieving a SASV-EER of 1.06% on the evaluation protocol of the SASV2022 challenge.
- Score: 63.42889348690095
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This study aims to develop a single integrated spoofing-aware speaker
verification (SASV) embeddings that satisfy two aspects. First, rejecting
non-target speakers' input as well as target speakers' spoofed inputs should be
addressed. Second, competitive performance should be demonstrated compared to
the fusion of automatic speaker verification (ASV) and countermeasure (CM)
embeddings, which outperformed single embedding solutions by a large margin in
the SASV2022 challenge. We analyze that the inferior performance of single SASV
embeddings comes from insufficient amount of training data and distinct nature
of ASV and CM tasks. To this end, we propose a novel framework that includes
multi-stage training and a combination of loss functions. Copy synthesis,
combined with several vocoders, is also exploited to address the lack of
spoofed data. Experimental results show dramatic improvements, achieving a
SASV-EER of 1.06% on the evaluation protocol of the SASV2022 challenge.
Related papers
- The SVASR System for Text-dependent Speaker Verification (TdSV) AAIC Challenge 2024 [0.0]
The proposed system incorporates a Fast-Conformer-based ASR module to validate speech content.
For speaker verification, we propose a feature fusion approach that combines speaker embeddings extracted from wav2vec-BERT and ReNet models.
arXiv Detail & Related papers (2024-11-25T10:53:45Z) - Bilingual Text-dependent Speaker Verification with Pre-trained Models for TdSV Challenge 2024 [0.0]
We present our submissions to the Iranian division of the Text-dependent Speaker Verification Challenge (TdSV) 2024.
TdSV aims to determine if a specific phrase was spoken by a target speaker.
For phrase verification, a phrase rejected incorrect phrases, while for speaker verification, a pre-trained ResNet293 with domain adaptation extracted speaker embeddings.
Whisper-PMFA, a pre-trained ASR model adapted for speaker verification, falls short of the performance of pre-trained ResNets.
arXiv Detail & Related papers (2024-11-16T15:53:03Z) - ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale [59.25180900687571]
ASVspoof 5 is the fifth edition in a series of challenges that promote the study of speech spoofing and deepfake attacks.
We describe the two challenge tracks, the new database, the evaluation metrics, and the evaluation platform, and present a summary of the results.
arXiv Detail & Related papers (2024-08-16T13:37:20Z) - Generalizing Speaker Verification for Spoof Awareness in the Embedding
Space [30.094557217931563]
ASV systems can be spoofed using various types of adversaries.
We propose a novel yet simple backend classifier based on deep neural networks.
Experiments are conducted on the ASVspoof 2019 logical access dataset.
arXiv Detail & Related papers (2024-01-20T07:30:22Z) - Tackling Spoofing-Aware Speaker Verification with Multi-Model Fusion [88.34134732217416]
This work focuses on fusion-based SASV solutions and proposes a multi-model fusion framework to leverage the power of multiple state-of-the-art ASV and CM models.
The proposed framework vastly improves the SASV-EER from 8.75% to 1.17%, which is 86% relative improvement compared to the best baseline system in the SASV challenge.
arXiv Detail & Related papers (2022-06-18T06:41:06Z) - Design Guidelines for Inclusive Speaker Verification Evaluation Datasets [0.6015898117103067]
Speaker verification (SV) provides billions of voice-enabled devices with access control, and ensures the security of voice-driven technologies.
Current SV evaluation practices are insufficient for evaluating bias: they are over-simplified and aggregate users, not representative of real-life usage scenarios.
This paper proposes design guidelines for constructing SV evaluation datasets that address these short-comings.
arXiv Detail & Related papers (2022-04-05T15:28:26Z) - ASVspoof 2021: accelerating progress in spoofed and deepfake speech
detection [70.45884214674057]
ASVspoof 2021 is the forth edition in the series of bi-annual challenges which aim to promote the study of spoofing.
This paper describes all three tasks, the new databases for each of them, the evaluation metrics, four challenge baselines, the evaluation platform and a summary of challenge results.
arXiv Detail & Related papers (2021-09-01T16:17:31Z) - ASVspoof 2021: Automatic Speaker Verification Spoofing and
Countermeasures Challenge Evaluation Plan [70.45884214674057]
ASVspoof 2021 is the 4th in a series of bi-annual, competitive challenges.
The goal is to develop countermeasures capable of discriminating between bona fide and spoofed or deepfake speech.
arXiv Detail & Related papers (2021-09-01T15:32:28Z) - Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning [95.60856995067083]
This work is among the first to perform adversarial defense for ASV without knowing the specific attack algorithms.
We propose to perform adversarial defense from two perspectives: 1) adversarial perturbation purification and 2) adversarial perturbation detection.
Experimental results show that our detection module effectively shields the ASV by detecting adversarial samples with an accuracy of around 80%.
arXiv Detail & Related papers (2021-06-01T07:10:54Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.