Training speaker recognition systems with limited data
arXiv:2203.14688 · doi:10.21437/Interspeech.2022-135
Abstract
This work considers training neural networks for speaker recognition with a much smaller dataset size compared to contemporary work. We artificially restrict the amount of data by proposing three subsets of the popular VoxCeleb2 dataset. These subsets are restricted to 50\,k audio files (versus over 1\,M files available), and vary on the axis of number of speakers and session variability. We train three speaker recognition systems on these subsets; the X-vector, ECAPA-TDNN, and wav2vec2 network architectures. We show that the self-supervised, pre-trained weights of wav2vec2 substantially improve performance when training data is limited. Code and data subsets are available at https://github.com/nikvaessen/w2v2-speaker-few-samples.
accepted to Interspeech 2022
References in corpus (6)
- WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
- SpeechBrain: A General-Purpose Speech Toolkit
- Reducing Transformer Depth on Demand with Structured Dropout
- Fine-tuning wav2vec2 for speaker recognition
- VoxSRC 2020: The Second VoxCeleb Speaker Recognition Challenge
- The Role of Phonetic Units in Speech Emotion Recognition