论文标题
Voxceleb扬声器识别挑战2022的Microsoft系统
The Microsoft System for VoxCeleb Speaker Recognition Challenge 2022
论文作者
论文摘要
在本报告中，我们描述了我们提交的Voxceleb扬声器识别挑战赛2（VoxSRC-22）的曲目系统。我们融合了各种良好的模型，这些模型从监督模型到自我保护的学习（SSL）预训练的模型。使用Voxceleb-2 Dev数据训练的有监督模型由ECAPA-TDNN和RES2NET组成，具有非常深的结构。 SSL预先训练的模型WAV2VEC和WAVLM经过大规模未标记的语音数据训练，最高可达百万小时。这些模型用ECAPA-TDNN级联，并以监督的方式进行了细微的调整，以提取说话者表示。所有13个模型均采用得分归一化和校准，然后融合到提交的系统中。我们还探索了校准阶段的音频质量度量，例如持续时间，SNR，T60和MOS。最好的提交系统以MindCF的价格达到0.073，在VoxSRC-22评估集中获得了1.436％的EER。
In this report, we describe our submitted system for track 2 of the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22). We fuse a variety of good-performing models ranging from supervised models to self-supervised learning(SSL) pre-trained models. The supervised models, trained using VoxCeleb-2 dev data, consist of ECAPA-TDNN and Res2Net in a very deep structure. The SSL pre-trained models, wav2vec and wavLM, are trained using large scale unlabeled speech data up to million hours. These models are cascaded with ECAPA-TDNN and further fine-tuned in a supervised fashion to extract the speaker representations. All 13 models are applied with score normalization and calibration and then fused into the the submitted system. We also explore the audio quality measures in the calibration stage such as duration, SNR, T60, and MOS. The best submitted system achieves 0.073 in minDCF and 1.436% in EER on the VoxSRC-22 evaluation set.
