All scripts regarding the ASV training in privacy/asv/asv_train, including parts of privacy/asv/asv.py, are based on the VoxCeleb recipe by SpeechBrain and adapted for LibriSpeech. The privacy evaluation metric is equal error rate (EER).

The ASR scripts are adapted from the Speechbrain recipe for LibriSpeech. The utility evaluation metric is word error rate (WER).

The SER scripts are adapted from the Speechbrain recipe for IEMOCAP. The utility evaluation metric is unweighted average recall (UAR).