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
- Asymmetric and trial-dependent modeling: the contribution of LIA to SdSV Challenge Task 2 [5.766624204597742]
This paper describes the contributions of our laboratory to the speaker recognition field.
The proposed approaches experimentally show their relevance and efficiency on the SdSv evaluation.
arXiv Detail & Related papers (2024-03-28T17:49:31Z) - 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) - MLCA-AVSR: Multi-Layer Cross Attention Fusion based Audio-Visual Speech Recognition [62.89464258519723]
We propose a multi-layer cross-attention fusion based AVSR approach that promotes representation of each modality by fusing them at different levels of audio/visual encoders.
Our proposed approach surpasses the first-place system, establishing a new SOTA cpCER of 29.13% on this dataset.
arXiv Detail & Related papers (2024-01-07T08:59:32Z) - Voice Spoofing Countermeasures: Taxonomy, State-of-the-art, experimental
analysis of generalizability, open challenges, and the way forward [2.393661358372807]
We conduct a review of the literature on spoofing detection using hand-crafted features, deep learning, end-to-end, and universal spoofing countermeasure solutions.
We report the performance of these countermeasures on several datasets and evaluate them across corpora.
arXiv Detail & Related papers (2022-10-02T03:53:37Z) - 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.