# Multi-Frequency Information Enhanced Channel Attention Module for Speaker Representation Learning

arXiv: https://arxiv.org/abs/2207.04540 · HTML: https://mlsanity.com/paper/2207.04540/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 10 Jul 2022.

## Builds on (most cited first, 21 of 21)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [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)
- [MUSAN: A Music, Speech, and Noise Corpus](https://mlsanity.com/paper/1510.08484/) (2015)
- [Generalized End-to-End Loss for Speaker Verification](https://mlsanity.com/paper/1710.10467/) (2017)
- [FcaNet: Frequency Channel Attention Networks](https://mlsanity.com/paper/2012.11879/) (2020)
- [In defence of metric learning for speaker recognition](https://mlsanity.com/paper/2003.11982/) (2020)
- [Attentive Statistics Pooling for Deep Speaker Embedding](https://mlsanity.com/paper/1803.10963/) (2018)
- [Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System](https://mlsanity.com/paper/1804.05160/) (2018)
- [Clova Baseline System for the VoxCeleb Speaker Recognition Challenge 2020](https://mlsanity.com/paper/2009.14153/) (2020)
- [Augmentation adversarial training for self-supervised speaker recognition](https://mlsanity.com/paper/2007.12085/) (2020)
- [Semi-Supervised Contrastive Learning with Generalized Contrastive Loss and Its Application to Speaker Recognition](https://mlsanity.com/paper/2006.04326/) (2020)
- [Self-Supervised Speaker Verification with Simple Siamese Network and Self-Supervised Regularization](https://mlsanity.com/paper/2112.04459/) (2021)
- [DEAAN: Disentangled Embedding and Adversarial Adaptation Network for Robust Speaker Representation Learning](https://mlsanity.com/paper/2012.06896/) (2020)
- [Generative Adversarial Speaker Embedding Networks for Domain Robust End-to-End Speaker Verification](https://mlsanity.com/paper/1811.03063/) (2018)
- [Open-set Short Utterance Forensic Speaker Verification using Teacher-Student Network with Explicit Inductive Bias](https://mlsanity.com/paper/2009.09556/) (2020)
- [Frequency and temporal convolutional attention for text-independent speaker recognition](https://mlsanity.com/paper/1910.07364/) (2019)

## Built on by (most cited first, 5 of 5)

- [Modality-agnostic Domain Generalizable Medical Image Segmentation by Multi-Frequency in Multi-Scale Attention](https://mlsanity.com/paper/2405.06284/) (2024)
- [M2SFormer: Multi-Spectral and Multi-Scale Attention with Edge-Aware Difficulty Guidance for Image Forgery Localization](https://mlsanity.com/paper/2506.20922/) (2025)
- [Improving Transformer-based Networks With Locality For Automatic Speaker Verification](https://mlsanity.com/paper/2302.08639/) (2023)
- [Toward Improving Synthetic Audio Spoofing Detection Robustness via Meta-Learning and Disentangled Training With Adversarial Examples](https://mlsanity.com/paper/2408.13341/) (2024)
- [UniPET-SPK: A Unified Framework for Parameter-Efficient Tuning of Pre-trained Speech Models for Robust Speaker Verification](https://mlsanity.com/paper/2501.16542/) (2025)

## Abstract (arXiv)

Recently, attention mechanisms have been applied successfully in neural network-based speaker verification systems. Incorporating the Squeeze-and-Excitation block into convolutional neural networks has achieved remarkable performance. However, it uses global average pooling (GAP) to simply average the features along time and frequency dimensions, which is incapable of preserving sufficient speaker information in the feature maps. In this study, we show that GAP is a special case of a discrete cosine transform (DCT) on time-frequency domain mathematically using only the lowest frequency component in frequency decomposition. To strengthen the speaker information extraction ability, we propose to utilize multi-frequency information and design two novel and effective attention modules, called Single-Frequency Single-Channel (SFSC) attention module and Multi-Frequency Single-Channel (MFSC) attention module. The proposed attention modules can effectively capture more speaker information from multiple frequency components on the basis of DCT. We conduct comprehensive experiments on the VoxCeleb datasets and a probe evaluation on the 1st 48-UTD forensic corpus. Experimental results demonstrate that our proposed SFSC and MFSC attention modules can efficiently generate more discriminative speaker representations and outperform ResNet34-SE and ECAPA-TDNN systems with relative 20.9% and 20.2% reduction in EER, without adding extra network parameters.