We propose a novel one-pass multiple ASR systems joint compression and quantization
approach using an all-in-one neural model. A single compression cycle allows multiple …

Knowledge distillation, a widely used model compression technique, works on the basis of
transferring knowledge from a cumbersome teacher model to a lightweight student model …

As a robust and large-scale multilingual speech recognition model, Whisper has
demonstrated impressive results in many low-resource and out-of-distribution scenarios …

This dissertation explores knowledge distillation techniques for end-to-end Automatic
Speech Recognition (ASR) models in resource-constrained environments. The aim is to …