Can You Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features? Apple Machine Learning Research
Self-supervised features are typically used in place of filter-bank features in speaker verification models. However, these models were originally designed to ingest filter-banks as inputs, and thus, training them on self-supervised features assumes that both feature types require the same amount of learning for the… Read More »Can You Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features? Apple Machine Learning Research