Utilizing Self-supervised Representations for MOS Prediction

Understand

Speech quality assessment has been a critical issue in speech processing for decades.

• Existing automatic evaluations usually require clean references or parallel ground truth data, which is infeasible when the amount of data soars.
• Subjective tests, on the other hand, do not need any additional clean or parallel data and correlates better to human perception.
• However, such a test is expensive and time-consuming because crowd work is necessary.