paper-with-me

홈 › Papers

Spectral-Aware Low-Rank Adaptation for Speaker Verification

2025-01-07 · Zhe Li, Man-Wai Mak, Mert Pilanci, Hung-Yi Lee, Helen Meng

Previous research has shown that the principal singular vectors of a pre-trained model's weight matrices capture critical knowledge. In contrast, those associated with small singular values may contain noise or less reliable information. As a result, the LoRA-based parameter-efficient fine-tuning (PEFT) approach, which does not constrain the use of the spectral space, may not be effective for tasks that demand high representation capacity. In this study, we enhance existing PEFT techniques by incorporating the spectral information of pre-trained weight matrices into the fine-tuning process. We investigate spectral adaptation strategies with a particular focus on the additive adjustment of top singular vectors. This is accomplished by applying singular value decomposition (SVD) to the pre-trained weight matrices and restricting the fine-tuning within the top spectral space. Extensive speaker verification experiments on VoxCeleb1 and CN-Celeb1 demonstrate enhanced tuning performance with the proposed approach. Code is released at https://github.com/lizhepolyu/SpectralFT.

📄 PDF Abstract BibTeX arXiv:2501.03829

Code (1)

lizhepolyu/spectralft 공식 구현 pytorch

Tasks

parameter-efficient fine-tuningSpeaker Verification

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Channel Adaptation for Speaker Verification Using Optimal Transport with Pseudo Label

2024-09-14 · Wenhao Yang, Jianguo Wei, Wenhuan Lu, Lei LI 외

Domain gap often degrades the performance of speaker verification (SV) systems when the statistical distributions of training data and real-world test speech are mismatched. Channel variation, a primary factor causing th…

Domain AdaptationPseudo LabelSpeaker VerificationUnsupervised Domain Adaptation

Large Audio Language Models for Spoofing-Aware Speaker Verification

2026-07-16 · Sofya Savelyeva, Mariia Perunova, Evgeny Kushnir, Artem Dvirniak 외 arxiv

Recent advances in text-to-speech and voice cloning make high-quality spoofing inexpensive and scalable, threatening voice authentication systems, especially automatic speaker verification (ASV). Existing defenses mainly…

Speaker VerificationDeepFake Detection

Robust Support Vector Machines for Speaker Verification Task

2013-06-12 · Kawthar Yasmine Zergat, Abderrahmane Amrouche

An important step in speaker verification is extracting features that best characterize the speaker voice. This paper investigates a front-end processing that aims at improving the performance of speaker verification bas…

Dimensionality ReductionSpeaker Verification

Multi-objective Progressive Clustering for Semi-supervised Domain Adaptation in Speaker Verification

2023-10-07 · Ze Li, Yuke Lin, Ning Jiang, Xiaoyi Qin 외

Utilizing the pseudo-labeling algorithm with large-scale unlabeled data becomes crucial for semi-supervised domain adaptation in speaker verification tasks. In this paper, we propose a novel pseudo-labeling method named …

ClusteringDenoisingDomain AdaptationSemi-supervised Domain Adaptation+1

What and When to Learn: CURriculum Ranking Loss for Large-Scale Speaker Verification

2026-03-25 · Massa Baali, Sarthak Bisht, Rita Singh, Bhiksha Raj arxiv

Speaker verification at large scale remains an open challenge as fixed-margin losses treat all samples equally regardless of quality. We hypothesize that mislabeled or degraded samples introduce noisy gradients that disr…

Speaker Verification