# Rethinking Leveraging Pre-Trained Multi-Layer Representations for Speaker Verification

arXiv: https://arxiv.org/abs/2512.22148 · HTML: https://mlsanity.com/paper/2512.22148/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 15 Dec 2025.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [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)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [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)
- [Additive Margin Softmax for Face Verification](https://mlsanity.com/paper/1801.05599/) (2018)
- [Attentive Statistics Pooling for Deep Speaker Embedding](https://mlsanity.com/paper/1803.10963/) (2018)
- [Exploring wav2vec 2.0 on speaker verification and language identification](https://mlsanity.com/paper/2012.06185/) (2020)
- [Large-scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification](https://mlsanity.com/paper/2110.05777/) (2021)
- [Building and Evaluation of a Real Room Impulse Response Dataset](https://mlsanity.com/paper/1811.06795/) (2018)
- [Fine-tuning wav2vec2 for speaker recognition](https://mlsanity.com/paper/2109.15053/) (2021)
- [The IDLAB VoxSRC-20 Submission: Large Margin Fine-Tuning and Quality-Aware Score Calibration in DNN Based Speaker Verification](https://mlsanity.com/paper/2010.11255/) (2020)
- [An attention-based backend allowing efficient fine-tuning of transformer models for speaker verification](https://mlsanity.com/paper/2210.01273/) (2022)
- [Multi-query multi-head attention pooling and Inter-topK penalty for speaker verification](https://mlsanity.com/paper/2110.05042/) (2021)
- [NeXt-TDNN: Modernizing Multi-Scale Temporal Convolution Backbone for Speaker Verification](https://mlsanity.com/paper/2312.08603/) (2023)
- [Layer-aware TDNN: Speaker Recognition Using Multi-Layer Features from Pre-Trained Models](https://mlsanity.com/paper/2409.07770/) (2024)

## Built on by (most cited first, 1 of 1)

- [MECT: Mixture of Experts with CNN-Transformer Network for Speaker verification](https://mlsanity.com/paper/2609.24061/) (2026)

## Abstract (arXiv)

Recent speaker verification studies have achieved notable success by leveraging layer-wise output from pre-trained Transformer models. However, few have explored the advancements in aggregating these multi-level features beyond the static weighted average. We present Layer Attentive Pooling (LAP), a novel strategy for aggregating inter-layer representations from pre-trained speech models for speaker verification. LAP assesses the significance of each layer from multiple perspectives time-dynamically, and employs max pooling instead of averaging. Additionally, we propose a lightweight backend speaker model comprising LAP and Attentive Statistical Temporal Pooling (ASTP) to extract speaker embeddings from pre-trained model output. Experiments on the VoxCeleb benchmark reveal that our compact architecture achieves state-of-the-art performance while greatly reducing the training time. We further analyzed LAP design and its dynamic weighting mechanism for capturing speaker characteristics.