# Utterance-level Aggregation For Speaker Recognition In The Wild

arXiv: https://arxiv.org/abs/1902.10107 · HTML: https://mlsanity.com/paper/1902.10107/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Feb 2019.

## Built on by (most cited first, 30 of 50)

- [AutoAD II: The Sequel -- Who, When, and What in Movie Audio Description](https://mlsanity.com/paper/2310.06838/) (2023)
- [Fusion and Orthogonal Projection for Improved Face-Voice Association](https://mlsanity.com/paper/2112.10483/) (2021)
- [Face, Body, Voice: Video Person-Clustering with Multiple Modalities](https://mlsanity.com/paper/2105.09939/) (2021)
- [A Multi-View Approach To Audio-Visual Speaker Verification](https://mlsanity.com/paper/2102.06291/) (2021)
- [Look Who's Talking: Active Speaker Detection in the Wild](https://mlsanity.com/paper/2108.07640/) (2021)
- [CommonAccent: Exploring Large Acoustic Pretrained Models for Accent Classification Based on Common Voice](https://mlsanity.com/paper/2305.18283/) (2023)
- [Attack on practical speaker verification system using universal adversarial perturbations](https://mlsanity.com/paper/2105.09022/) (2021)
- [Winning solutions and post-challenge analyses of the ChaLearn AutoDL challenge 2019](https://mlsanity.com/paper/2201.03801/) (2022)
- [Single-branch Network for Multimodal Training](https://mlsanity.com/paper/2303.06129/) (2023)
- [Disentangling Voice and Content with Self-Supervision for Speaker Recognition](https://mlsanity.com/paper/2310.01128/) (2023)
- [Multi-task Voice Activated Framework using Self-supervised Learning](https://mlsanity.com/paper/2110.01077/) (2021)
- [The VoxCeleb Speaker Recognition Challenge: A Retrospective](https://mlsanity.com/paper/2408.14886/) (2024)
- [PAEFF: Precise Alignment and Enhanced Gated Feature Fusion for Face-Voice Association](https://mlsanity.com/paper/2505.17002/) (2025)
- [Multi-View Self-Attention Based Transformer for Speaker Recognition](https://mlsanity.com/paper/2110.05036/) (2021)
- [Face-voice Association in Multilingual Environments (FAME) 2026 Challenge Evaluation Plan](https://mlsanity.com/paper/2508.04592/) (2025)
- [Dictionary Attacks on Speaker Verification](https://mlsanity.com/paper/2204.11304/) (2022)
- [Enrollment-stage Backdoor Attacks on Speaker Recognition Systems via Adversarial Ultrasound](https://mlsanity.com/paper/2306.16022/) (2023)
- [Linking Faces and Voices Across Languages: Insights from the FAME 2026 Challenge](https://mlsanity.com/paper/2512.20376/) (2025)
- [OS-MSL: One Stage Multimodal Sequential Link Framework for Scene Segmentation and Classification](https://mlsanity.com/paper/2207.01241/) (2022)
- [Face-voice Association in Multilingual Environments (FAME) Challenge 2024 Evaluation Plan](https://mlsanity.com/paper/2404.09342/) (2024)
- [Modality Invariant Multimodal Learning to Handle Missing Modalities: A Single-Branch Approach](https://mlsanity.com/paper/2408.07445/) (2024)
- [EfficientTDNN: Efficient Architecture Search for Speaker Recognition](https://mlsanity.com/paper/2103.13581/) (2021)
- [Fusion of Embeddings Networks for Robust Combination of Text Dependent and Independent Speaker Recognition](https://mlsanity.com/paper/2106.10169/) (2021)
- [Learning Branched Fusion and Orthogonal Projection for Face-Voice Association](https://mlsanity.com/paper/2208.10238/) (2022)
- [Audio Representation Learning by Distilling Video as Privileged Information](https://mlsanity.com/paper/2302.02845/) (2023)
- [Experimenting with Additive Margins for Contrastive Self-Supervised Speaker Verification](https://mlsanity.com/paper/2306.03664/) (2023)
- [Additive Margin in Contrastive Self-Supervised Frameworks to Learn Discriminative Speaker Representations](https://mlsanity.com/paper/2404.14913/) (2024)
- [SpeechNAS: Towards Better Trade-off between Latency and Accuracy for Large-Scale Speaker Verification](https://mlsanity.com/paper/2109.08839/) (2021)
- [Audio-video fusion strategies for active speaker detection in meetings](https://mlsanity.com/paper/2206.10411/) (2022)
- [Defend Data Poisoning Attacks on Voice Authentication](https://mlsanity.com/paper/2209.04547/) (2022)

## Abstract (arXiv)

The objective of this paper is speaker recognition "in the wild"-where utterances may be of variable length and also contain irrelevant signals. Crucial elements in the design of deep networks for this task are the type of trunk (frame level) network, and the method of temporal aggregation. We propose a powerful speaker recognition deep network, using a "thin-ResNet" trunk architecture, and a dictionary-based NetVLAD or GhostVLAD layer to aggregate features across time, that can be trained end-to-end. We show that our network achieves state of the art performance by a significant margin on the VoxCeleb1 test set for speaker recognition, whilst requiring fewer parameters than previous methods. We also investigate the effect of utterance length on performance, and conclude that for "in the wild" data, a longer length is beneficial.