# ECAPA2: A Hybrid Neural Network Architecture and Training Strategy for Robust Speaker Embeddings

arXiv: https://arxiv.org/abs/2401.08342 · HTML: https://mlsanity.com/paper/2401.08342/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jan 2024.

## Built on by (most cited first, 22 of 22)

- [XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model](https://mlsanity.com/paper/2406.04904/) (2024)
- [The VoicePrivacy 2024 Challenge Evaluation Plan](https://mlsanity.com/paper/2404.02677/) (2024)
- [SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model](https://mlsanity.com/paper/2505.15670/) (2025)
- [NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference](https://mlsanity.com/paper/2508.05835/) (2025)
- [The Third VoicePrivacy Challenge: Preserving Emotional Expressiveness and Linguistic Content in Voice Anonymization](https://mlsanity.com/paper/2601.11846/) (2026)
- [Multilingual Source Tracing of Speech Deepfakes: A First Benchmark](https://mlsanity.com/paper/2508.04143/) (2025)
- [SVeritas: Benchmark for Robust Speaker Verification under Diverse Conditions](https://mlsanity.com/paper/2509.17091/) (2025)
- [Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors](https://mlsanity.com/paper/2407.11828/) (2024)
- [kNN Retrieval for Simple and Effective Zero-Shot Multi-speaker Text-to-Speech](https://mlsanity.com/paper/2408.10771/) (2024)
- [From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition](https://mlsanity.com/paper/2505.16972/) (2025)
- [ProMode: A Speech Prosody Model Conditioned on Acoustic and Textual Inputs](https://mlsanity.com/paper/2508.09389/) (2025)
- [Target speaker anonymization in multi-speaker recordings](https://mlsanity.com/paper/2510.09307/) (2025)
- [BnTTS: Few-Shot Speaker Adaptation in Low-Resource Setting](https://mlsanity.com/paper/2502.05729/) (2025)
- [Voice Adaptation for Swiss German](https://mlsanity.com/paper/2505.22054/) (2025)
- [DAME: Duration-Aware Matryoshka Embedding for Duration-Robust Speaker Verification](https://mlsanity.com/paper/2601.13999/) (2026)
- [Enhancing Speaker Verification with Whispered Speech via Post-Processing](https://mlsanity.com/paper/2604.20229/) (2026)
- [On Low-Bit Quantization Errors in Speaker Verification: Diagnostic and Mitigation](https://mlsanity.com/paper/2606.08078/) (2026)
- [Kiwano: A Cutting-Edge Open-Source Toolkit for Speaker Verification](https://mlsanity.com/paper/2606.22369/) (2026)
- [Large Audio Language Models for Spoofing-Aware Speaker Verification](https://mlsanity.com/paper/2607.14753/) (2026)
- [Your Voice Cloning System is Secretly a Voice Anonymizer](https://mlsanity.com/paper/2608.27360/) (2026)
- [MECT: Mixture of Experts with CNN-Transformer Network for Speaker verification](https://mlsanity.com/paper/2609.24061/) (2026)
- [Learnable Classifier-Free Guidance Null Embeddings for Enhanced Controllable Speech Synthesis](https://mlsanity.com/paper/2609.25411/) (2026)

## Abstract (arXiv)

In this paper, we present ECAPA2, a novel hybrid neural network architecture and training strategy to produce robust speaker embeddings. Most speaker verification models are based on either the 1D- or 2D-convolutional operation, often manifested as Time Delay Neural Networks or ResNets, respectively. Hybrid models are relatively unexplored without an intuitive explanation what constitutes best practices in regard to its architectural choices. We motivate the proposed ECAPA2 model in this paper with an analysis of current speaker verification architectures. In addition, we propose a training strategy which makes the speaker embeddings more robust against overlapping speech and short utterance lengths. The presented ECAPA2 architecture and training strategy attains state-of-the-art performance on the VoxCeleb1 test sets with significantly less parameters than current models. Finally, we make a pre-trained model publicly available to promote research on downstream tasks.