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.

翻译：本研究探讨在远小于当前主流工作的数据集规模下训练说话人识别神经网络。我们通过从广泛使用的VoxCeleb2数据集中划分出三个子集来人为限制数据量：这些子集仅包含5万条音频文件（而原始数据集拥有超过100万条可用文件），并在说话人数量与会话变异性两个维度上呈现差异。我们基于上述子集训练了三种说话人识别系统，分别采用X-vector、ECAPA-TDNN和wav2vec2网络架构。实验表明，在训练数据受限的情况下，wav2vec2的自监督预训练权重能显著提升系统性能。相关代码与数据集子集已开源至https://github.com/nikvaessen/w2v2-speaker-few-samples。