# MECT: Mixture of Experts with CNN-Transformer Network for Speaker verification

arXiv: https://arxiv.org/abs/2609.24061 · HTML: https://mlsanity.com/paper/2609.24061/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal MoE models, one of 12 directions in Mixture-of-experts.
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 21 Sep 2026.

## Placed in

- Mixture-of-experts / [Multimodal MoE models](https://mlsanity.com/moe/multimodal-moe-models/)

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [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)
- [Attentive Statistics Pooling for Deep Speaker Embedding](https://mlsanity.com/paper/1803.10963/) (2018)
- [CAM++: A Fast and Efficient Network for Speaker Verification Using Context-Aware Masking](https://mlsanity.com/paper/2303.00332/) (2023)
- [Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit](https://mlsanity.com/paper/2210.17016/) (2022)
- [BUT System Description to VoxCeleb Speaker Recognition Challenge 2019](https://mlsanity.com/paper/1910.12592/) (2019)
- [CN-CELEB: a challenging Chinese speaker recognition dataset](https://mlsanity.com/paper/1911.01799/) (2019)
- [MFA-Conformer: Multi-scale Feature Aggregation Conformer for Automatic Speaker Verification](https://mlsanity.com/paper/2203.15249/) (2022)
- [Building and Evaluation of a Real Room Impulse Response Dataset](https://mlsanity.com/paper/1811.06795/) (2018)
- [An Enhanced Res2Net with Local and Global Feature Fusion for Speaker Verification](https://mlsanity.com/paper/2305.12838/) (2023)
- [Reshape Dimensions Network for Speaker Recognition](https://mlsanity.com/paper/2407.18223/) (2024)
- [VoxBlink2: A 100K+ Speaker Recognition Corpus and the Open-Set Speaker-Identification Benchmark](https://mlsanity.com/paper/2407.11510/) (2024)
- [ECAPA2: A Hybrid Neural Network Architecture and Training Strategy for Robust Speaker Embeddings](https://mlsanity.com/paper/2401.08342/) (2024)
- [3D-Speaker-Toolkit: An Open-Source Toolkit for Multimodal Speaker Verification and Diarization](https://mlsanity.com/paper/2403.19971/) (2024)
- [Multi-View Self-Attention Based Transformer for Speaker Recognition](https://mlsanity.com/paper/2110.05036/) (2021)
- [PCF: ECAPA-TDNN with Progressive Channel Fusion for Speaker Verification](https://mlsanity.com/paper/2303.00204/) (2023)
- [Golden Gemini is All You Need: Finding the Sweet Spots for Speaker Verification](https://mlsanity.com/paper/2312.03620/) (2023)
- [Exploring Binary Classification Loss For Speaker Verification](https://mlsanity.com/paper/2307.08205/) (2023)
- [NeXt-TDNN: Modernizing Multi-Scale Temporal Convolution Backbone for Speaker Verification](https://mlsanity.com/paper/2312.08603/) (2023)
- [Enhancing Speaker Verification with w2v-BERT 2.0 and Knowledge Distillation guided Structured Pruning](https://mlsanity.com/paper/2510.04213/) (2025)
- [ReDimNet2: Scaling Speaker Verification via Time-Pooled Dimension Reshaping](https://mlsanity.com/paper/2603.11841/) (2026)
- [Rethinking Leveraging Pre-Trained Multi-Layer Representations for Speaker Verification](https://mlsanity.com/paper/2512.22148/) (2025)

## Abstract (arXiv)

In this paper, we propose MECT, a speaker verification model that integrates the Mixture-of-Experts (MoE) mechanism into a CNN-Transformer backbone with optimized block structure and stacking scheme. Specifically, we investigated four MoE variants that span utterance-level and frame-level granularity with dense and sparse routing strategies. The MoE mechanism proves to be effective over the baseline without MoE with only a small increase in parameters. We further scale MECT to a series of model sizes, all maintaining compact parameters and low computational complexity. In particular, MECT-B2 achieves state-of-the-art performance on VoxCeleb1 and delivers strong results on CN-Celeb, demonstrating its effectiveness across diverse datasets. In addition, we establish a streaming inference paradigm through causal retraining, which maintains strong performance at a chunk size of 100ms.