# Frequency and Multi-Scale Selective Kernel Attention for Speaker Verification

arXiv: https://arxiv.org/abs/2204.01005 · HTML: https://mlsanity.com/paper/2204.01005/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 27 references that are in the map.
- First posted on arXiv 3 Apr 2022.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [Res2Net: A New Multi-scale Backbone Architecture](https://mlsanity.com/paper/1904.01169/) (2019)
- [ResNeSt: Split-Attention Networks](https://mlsanity.com/paper/2004.08955/) (2020)
- [MUSAN: A Music, Speech, and Noise Corpus](https://mlsanity.com/paper/1510.08484/) (2015)
- [Selective Kernel Networks](https://mlsanity.com/paper/1903.06586/) (2019)
- [Dynamic Convolution: Attention over Convolution Kernels](https://mlsanity.com/paper/1912.03458/) (2019)
- [Generalized End-to-End Loss for Speaker Verification](https://mlsanity.com/paper/1710.10467/) (2017)
- [In defence of metric learning for speaker recognition](https://mlsanity.com/paper/2003.11982/) (2020)
- [Pushing the limits of raw waveform speaker recognition](https://mlsanity.com/paper/2203.08488/) (2022)
- [Clova Baseline System for the VoxCeleb Speaker Recognition Challenge 2020](https://mlsanity.com/paper/2009.14153/) (2020)
- [RawNet: Advanced end-to-end deep neural network using raw waveforms for text-independent speaker verification](https://mlsanity.com/paper/1904.08104/) (2019)
- [MFA: TDNN with Multi-scale Frequency-channel Attention for Text-independent Speaker Verification with Short Utterances](https://mlsanity.com/paper/2202.01624/) (2022)
- [Integrating Frequency Translational Invariance in TDNNs and Frequency Positional Information in 2D ResNets to Enhance Speaker Verification](https://mlsanity.com/paper/2104.02370/) (2021)
- [RawNeXt: Speaker verification system for variable-duration utterances with deep layer aggregation and extended dynamic scaling policies](https://mlsanity.com/paper/2112.07935/) (2021)
- [RSKNet-MTSP: Effective and Portable Deep Architecture for Speaker Verification](https://mlsanity.com/paper/2108.13249/) (2021)
- [TMS: A Temporal Multi-scale Backbone Design for Speaker Embedding](https://mlsanity.com/paper/2203.09098/) (2022)
- [Decomposed Temporal Dynamic CNN: Efficient Time-Adaptive Network for Text-Independent Speaker Verification Explained with Speaker Activation Map](https://mlsanity.com/paper/2203.15277/) (2022)

## Built on by (most cited first, 10 of 10)

- [ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models](https://mlsanity.com/paper/2401.17230/) (2024)
- [SpoofCeleb: Speech Deepfake Detection and SASV In The Wild](https://mlsanity.com/paper/2409.17285/) (2024)
- [Disentangling Voice and Content with Self-Supervision for Speaker Recognition](https://mlsanity.com/paper/2310.01128/) (2023)
- [Towards single integrated spoofing-aware speaker verification embeddings](https://mlsanity.com/paper/2305.19051/) (2023)
- [t-EER: Parameter-Free Tandem Evaluation of Countermeasures and Biometric Comparators](https://mlsanity.com/paper/2309.12237/) (2023)
- [PDAF: A Phonetic Debiasing Attention Framework For Speaker Verification](https://mlsanity.com/paper/2409.05799/) (2024)
- [To what extent can ASV systems naturally defend against spoofing attacks?](https://mlsanity.com/paper/2406.05339/) (2024)
- [SLAM in the Dark: Self-Supervised Learning of Pose, Depth and Loop-Closure from Thermal Images](https://mlsanity.com/paper/2502.18932/) (2025)
- [DAME: Duration-Aware Matryoshka Embedding for Duration-Robust Speaker Verification](https://mlsanity.com/paper/2601.13999/) (2026)
- [DFKI-Speech System for WildSpoof Challenge: A robust framework for SASV In-the-Wild](https://mlsanity.com/paper/2602.02286/) (2026)

## Abstract (arXiv)

The majority of recent state-of-the-art speaker verification architectures adopt multi-scale processing and frequency-channel attention mechanisms. Convolutional layers of these models typically have a fixed kernel size, e.g., 3 or 5. In this study, we further contribute to this line of research utilising a selective kernel attention (SKA) mechanism. The SKA mechanism allows each convolutional layer to adaptively select the kernel size in a data-driven fashion. It is based on an attention mechanism which exploits both frequency and channel domain. We first apply existing SKA module to our baseline. Then we propose two SKA variants where the first variant is applied in front of the ECAPA-TDNN model and the other is combined with the Res2net backbone block. Through extensive experiments, we demonstrate that our two proposed SKA variants consistently improves the performance and are complementary when tested on three different evaluation protocols.