# Attentive Statistics Pooling for Deep Speaker Embedding

arXiv: https://arxiv.org/abs/1803.10963 · HTML: https://mlsanity.com/paper/1803.10963/

## Key facts

- Cited by 114 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Mar 2018.

## Built on by (most cited first, 30 of 114)

- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [A Large-Scale Evaluation of Speech Foundation Models](https://mlsanity.com/paper/2404.09385/) (2024)
- [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)
- [CommonAccent: Exploring Large Acoustic Pretrained Models for Accent Classification Based on Common Voice](https://mlsanity.com/paper/2305.18283/) (2023)
- [Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-spoofing](https://mlsanity.com/paper/2504.05657/) (2025)
- [Self-Supervised Speaker Verification with Simple Siamese Network and Self-Supervised Regularization](https://mlsanity.com/paper/2112.04459/) (2021)
- [Partially Fake Audio Detection by Self-attention-based Fake Span Discovery](https://mlsanity.com/paper/2202.06684/) (2022)
- [Disentangling Voice and Content with Self-Supervision for Speaker Recognition](https://mlsanity.com/paper/2310.01128/) (2023)
- [Voting for the right answer: Adversarial defense for speaker verification](https://mlsanity.com/paper/2106.07868/) (2021)
- [Deepfake audio detection by speaker verification](https://mlsanity.com/paper/2209.14098/) (2022)
- [Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs](https://mlsanity.com/paper/2512.08417/) (2025)
- [Multi-task Voice Activated Framework using Self-supervised Learning](https://mlsanity.com/paper/2110.01077/) (2021)
- [Improving the Training Recipe for a Robust Conformer-based Hybrid Model](https://mlsanity.com/paper/2206.12955/) (2022)
- [VoxSRC 2022: The Fourth VoxCeleb Speaker Recognition Challenge](https://mlsanity.com/paper/2302.10248/) (2023)
- [Boosting Graph Pooling with Persistent Homology](https://mlsanity.com/paper/2402.16346/) (2024)
- [Enhancing Partially Spoofed Audio Localization with Boundary-aware Attention Mechanism](https://mlsanity.com/paper/2407.21611/) (2024)
- [The VoxCeleb Speaker Recognition Challenge: A Retrospective](https://mlsanity.com/paper/2408.14886/) (2024)
- [Multi-View Self-Attention Based Transformer for Speaker Recognition](https://mlsanity.com/paper/2110.05036/) (2021)
- [STC speaker recognition systems for the NIST SRE 2021](https://mlsanity.com/paper/2111.02298/) (2021)
- [Combining Automatic Speaker Verification and Prosody Analysis for Synthetic Speech Detection](https://mlsanity.com/paper/2210.17222/) (2022)
- [CoverHunter: Cover Song Identification with Refined Attention and Alignments](https://mlsanity.com/paper/2306.09025/) (2023)
- [Towards Effective and Compact Contextual Representation for Conformer Transducer Speech Recognition Systems](https://mlsanity.com/paper/2306.13307/) (2023)
- [Leveraging ASR Pretrained Conformers for Speaker Verification through Transfer Learning and Knowledge Distillation](https://mlsanity.com/paper/2309.03019/) (2023)
- [USAT: A Universal Speaker-Adaptive Text-to-Speech Approach](https://mlsanity.com/paper/2404.18094/) (2024)
- [ECAPA-TDNN for Multi-speaker Text-to-speech Synthesis](https://mlsanity.com/paper/2203.10473/) (2022)
- [Multi-Frequency Information Enhanced Channel Attention Module for Speaker Representation Learning](https://mlsanity.com/paper/2207.04540/) (2022)
- [Generalizable Zero-Shot Speaker Adaptive Speech Synthesis with Disentangled Representations](https://mlsanity.com/paper/2308.13007/) (2023)
- [Exploring Pathological Speech Quality Assessment with ASR-Powered Wav2Vec2 in Data-Scarce Context](https://mlsanity.com/paper/2403.20184/) (2024)
- [Serialized Multi-Layer Multi-Head Attention for Neural Speaker Embedding](https://mlsanity.com/paper/2107.06493/) (2021)
- [SVSNet: An End-to-end Speaker Voice Similarity Assessment Model](https://mlsanity.com/paper/2107.09392/) (2021)

## Abstract (arXiv)

This paper proposes attentive statistics pooling for deep speaker embedding in text-independent speaker verification. In conventional speaker embedding, frame-level features are averaged over all the frames of a single utterance to form an utterance-level feature. Our method utilizes an attention mechanism to give different weights to different frames and generates not only weighted means but also weighted standard deviations. In this way, it can capture long-term variations in speaker characteristics more effectively. An evaluation on the NIST SRE 2012 and the VoxCeleb data sets shows that it reduces equal error rates (EERs) from the conventional method by 7.5% and 8.1%, respectively.