Short-segment Speaker Verification With Pre-trained Models And Multi-resolution Encoder

Abstract

Speaker verification (SV) utilizing features obtained from models pre-trained via self-supervised learning has recently demonstrated impressive performances. However, these pre-trained models (PTMs) usually have a temporal resolution of 20 ms, which is lower than typical filterbank features. It may be problematic especially for short-segment SV with an input segment shorter than 2 s, in which we need to extract as much information as possible from the input with a limited length. Although there have been approaches to utilize multi-resolution features from the HuBERT models, the window shifts were 20, 40, and 100 ms when the sampling rate was 16 kHz and thus only lower resolution features were considered. In this study, we propose an SV system which utilizes PTM features along with filterbank features and those from the multi-resolution time domain encoder with window shifts of 1.56, 3.13, 6.25, and 12.5 ms. Experimental results on the VoxCeleb dataset with various input lengths showed

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymyoung2025short

Related papers

• A Unified Deep Learning Framework For Short-duration Speaker Verification In Adverse Environments (2020)9.41
• An Attention-based Backend Allowing Efficient Fine-tuning Of Transformer Models For Speaker Verification (2022)11.08
• Universal Speaker Recognition Encoders For Different Speech Segments Duration (2022)4.52
• Enhancing Speaker Verification With W2v-bert 2.0 And Knowledge Distillation Guided Structured Pruning (2025)3.33
• Eres2netv2: Boosting Short-duration Speaker Verification Performance With Computational Efficiency (2024)9.41
• Deep Segment Attentive Embedding For Duration Robust Speaker Verification (2018)2.26
• Improving Multi-scale Aggregation Using Feature Pyramid Module For Robust Speaker Verification Of Variable-duration Utterances (2020)10.48
• Mr-rawnet: Speaker Verification System With Multiple Temporal Resolutions For Variable Duration Utterances Using Raw Waveforms (2024)2.26