Collaborative Training of Acoustic Encoders for Speech Recognition

Understand

On-device speech recognition requires training models of different sizes for deploying on devices with various computational budgets.

• When building such different models, we can benefit from training them jointly to take advantage of the knowledge shared between them.
• Joint training is also efficient since it reduces the redundancy in the training procedure's data handling operations.
• We propose a method for collaboratively training acoustic encoders of different sizes for speech recognition.