Result Details
CA-MHFA: A Context-Aware Multi-Head Factorized Attentive Pooling for SSL-Based Speaker Verification
Mošner Ladislav, Ing., DCGM (FIT)
Zhang Lin, Ph.D.
Plchot Oldřich, Ing., Ph.D., DCGM (FIT)
Stafylakis Themos
Burget Lukáš, doc. Ing., Ph.D., DCGM (FIT)
Černocký Jan, prof. Dr. Ing., DCGM (FIT)
Self-supervised learning (SSL) models for speaker verifica- tion (SV) have gained
significant attention in recent years. However, existing SSL-based SV systems
often struggle to capture local temporal dependencies and generalize across
different tasks. In this paper, we pro- pose context-aware multi-head factorized
attentive pooling (CA-MHFA), a lightweight framework that incorporates contextual
information from surrounding frames. CA-MHFA leverages grouped, learnable queries
to effectively model contextual dependencies while maintaining efficiency by
sharing keys and values across groups. Experimental results on the VoxCeleb
dataset show that CA-MHFA achieves EERs of 0.42%, 0.48%, and 0.96% on Vox1-O,
Vox1-E, and Vox1-H, respectively, outperforming complex models like WavLM-TDNN
with fewer parameters and faster convergence. Additionally, CA-MHFA demonstrates
strong generalization across multiple SSL models and tasks, including emotion
recognition and anti-spoofing, highlighting its robustness and versatility.
Self-supervised learning, speaker verification, speaker extractor, pooling
mechanism, speech classification
@inproceedings{BUT198050,
author="Junyi {Peng} and Ladislav {Mošner} and Lin {Zhang} and Oldřich {Plchot} and Themos {Stafylakis} and Lukáš {Burget} and Jan {Černocký}",
title="CA-MHFA: A Context-Aware Multi-Head Factorized Attentive Pooling for SSL-Based Speaker Verification",
booktitle="ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
year="2025",
pages="1--5",
publisher="IEEE Signal Processing Society",
address="Hyderabad",
doi="10.1109/ICASSP49660.2025.10889058",
isbn="979-8-3503-6874-1",
url="https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10889058"
}Exchanges for SPEech ReseArch aNd TechnOlogies, EU, Horizon 2020, start: 2021-01-01, end: 2025-12-31, running
Linguistics, Artificial Intelligence and Language and Speech Technologies: from Research to Applications, EU, MEZISEKTOROVÁ SPOLUPRÁCE, EH23_020/0008518, start: 2025-01-01, end: 2028-12-31, running
Robust processing of recordings for operations and security, MV, PROGRAM STRATEGICKÁ PODPORA ROZVOJE BEZPEČNOSTNÍHO VÝZKUMU ČR 2019-2025 (IMPAKT 1) PODPROGRAMU 1 SPOLEČNÉ VÝZKUMNÉ PROJEKTY (BV IMP1/1VS), VJ01010108, start: 2020-10-01, end: 2025-09-30, completed