Beyond Short Segments : Expanding Speaker Embeddings with Vector Archives
Not on the map. Why?
Abstract (arXiv)
The performance of state-of-the-art speaker verification (SV) systems severely degrades on short utterances due to insufficient speaker-specific information. To address this critical challenge, we propose the Vector Archive Mapping ECAPA (VAM-ECAPA), a novel system designed to enhance feature extraction from short-duration speech. The core of our system is the Transformer-based Vector Archive Mapping with Statistical Pooling (TVAMSP) module, which enriches information-scarce features by mapping them against a learnable Vector Archive of canonical speaker traits. By integrating the TVAMSP module into a strong WavLM+ECAPA-TDNN baseline, our system learns to map sparse features from short segments into robust, discriminative speaker representations. Experiments on the VoxCeleb1 benchmark show that our proposed VAM-ECAPA achieves a highly competitive EER of 8.334% on 1-second test segments, a 54.8% relative error reduction compared to a conventionally-trained baseline.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 28 of its 40 references that are in the map. First posted on arXiv 26 Jul 2026.
Builds on
28 of 40 references.
References · 28
- 2017Attention Is All You Needcited by 60,361
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
- 2017Squeeze-and-Excitation Networkscited by 4,789
- 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
- 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
- 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
- 2018VoxCeleb2: Deep Speaker Recognitioncited by 875
- 2021SUPERB: Speech processing Universal PERformance Benchmarkcited by 666
- 2014Neural Turing Machinescited by 644
- 2020ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verificationcited by 628
- 2019Res2Net: A New Multi-scale Backbone Architecturecited by 470
- 2015MUSAN: A Music, Speech, and Noise Corpuscited by 425
16 more
- 2017Generalized End-to-End Loss for Speaker Verificationcited by 293
- 2018Additive Margin Softmax for Face Verificationcited by 278
- 2018Attentive Statistics Pooling for Deep Speaker Embeddingcited by 114
- 2020Exploring wav2vec 2.0 on speaker verification and language identificationcited by 95
- 2023ICASSP 2023 Deep Noise Suppression Challengecited by 65
- 2020Speaker Recognition Based on Deep Learning: An Overviewcited by 59
- 2019Utterance-level Aggregation For Speaker Recognition In The Wildcited by 50
- 2018Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition Systemcited by 47
- 2022Why does Self-Supervised Learning for Speech Recognition Benefit Speaker Recognition?cited by 27
- 2020The IDLAB VoxSRC-20 Submission: Large Margin Fine-Tuning and Quality-Aware Score Calibration in DNN Based Speaker Verificationcited by 23
- 2023Self-Supervised Learning with Cluster-Aware-DINO for High-Performance Robust Speaker Verificationcited by 11
- 2017Efficient Implementation of the Room Simulator for Training Deep Neural Network Acoustic Modelscited by 9
- 2020Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairscited by 8
- 2018Frame-level speaker embeddings for text-independent speaker recognition and analysis of end-to-end modelcited by 5
- 2020Segment Aggregation for short utterances speaker verification using raw waveformscited by 2
- 2020Length- and Noise-aware Training Techniques for Short-utterance Speaker Recognitioncited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.