# Graph attentive feature aggregation for text-independent speaker verification

arXiv: https://arxiv.org/abs/2112.12343 · HTML: https://mlsanity.com/paper/2112.12343/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Dec 2021.

## Built on by (most cited first, 4 of 4)

- [One-Step Knowledge Distillation and Fine-Tuning in Using Large Pre-Trained Self-Supervised Learning Models for Speaker Verification](https://mlsanity.com/paper/2305.17394/) (2023)
- [Audio Deepfake Attribution: An Initial Dataset and Investigation](https://mlsanity.com/paper/2208.10489/) (2022)
- [DS-TDNN: Dual-stream Time-delay Neural Network with Global-aware Filter for Speaker Verification](https://mlsanity.com/paper/2303.11020/) (2023)
- [Betray Oneself: A Novel Audio DeepFake Detection Model via Mono-to-Stereo Conversion](https://mlsanity.com/paper/2305.16353/) (2023)

## Abstract (arXiv)

The objective of this paper is to combine multiple frame-level features into a single utterance-level representation considering pairwise relationship. For this purpose, we propose a novel graph attentive feature aggregation module by interpreting each frame-level feature as a node of a graph. The inter-relationship between all possible pairs of features, typically exploited indirectly, can be directly modeled using a graph. The module comprises a graph attention layer and a graph pooling layer followed by a readout operation. The graph attention layer first models the non-Euclidean data manifold between different nodes. Then, the graph pooling layer discards less informative nodes considering the significance of the nodes. Finally, the readout operation combines the remaining nodes into a single representation. We employ two recent systems, SE-ResNet and RawNet2, with different input features and architectures and demonstrate that the proposed feature aggregation module consistently shows a relative improvement over 10%, compared to the baseline.