Leveraging In-the-wild Data For Effective Self-supervised Pretraining In Speaker Recognition

Abstract

Current speaker recognition systems primarily rely on supervised approaches, constrained by the scale of labeled datasets. To boost the system performance, researchers leverage large pretrained models such as WavLM to transfer learned high-level features to the downstream speaker recognition task. However, this approach introduces extra parameters as the pretrained model remains in the inference stage. Another group of researchers directly apply self-supervised methods such as DINO to speaker embedding learning, yet they have not explored its potential on large-scale in-the-wild datasets. In this paper, we present the effectiveness of DINO training on the large-scale WenetSpeech dataset and its transferability in enhancing the supervised system performance on the CNCeleb dataset. Additionally, we introduce a confidence-based data filtering algorithm to remove unreliable data from the pretraining dataset, leading to better performance with less training data. The associated pretrained m

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keywang2023leveraging

Related papers

• Self-supervised Learning With Cluster-aware-dino For High-performance Robust Speaker Verification (2023)0.00
• Pushing The Limits Of Self-supervised Speaker Verification Using Regularized Distillation Framework (2022)17.00
• Curriculum Learning For Self-supervised Speaker Verification (2022)8.09
• Wavlm: Large-scale Self-supervised Pre-training For Full Stack Speech Processing (2021)24.00
• Weakly-supervised Speech Pre-training: A Case Study On Target Speech Recognition (2023)8.09
• DINO-VITS: Data-efficient Zero-shot TTS With Self-supervised Speaker Verification Loss For Noise Robustness (2023)3.58
• Training Speaker Recognition Systems With Limited Data (2022)8.13
• Whisper Speaker Identification: Leveraging Pre-trained Multilingual Transformers For Robust Speaker Embeddings (2025)0.00