Decouple Non-parametric Knowledge Distillation For End-to-end Speech Translation
This addresses data efficiency in speech translation for scenarios where transcriptions are unavailable, representing an incremental advance.
The paper tackles the problem of improving speech translation model performance without requiring transcriptions during training, by proposing Decoupled Non-parametric Knowledge Distillation (DNKD), which achieves consistent improvements over a strong baseline on the MuST-C corpus.
Existing techniques often attempt to make knowledge transfer from a powerful machine translation (MT) to speech translation (ST) model with some elaborate techniques, which often requires transcription as extra input during training. However, transcriptions are not always available, and how to improve the ST model performance without transcription, i.e., data efficiency, has rarely been studied in the literature. In this paper, we propose Decoupled Non-parametric Knowledge Distillation (DNKD) from data perspective to improve the data efficiency. Our method follows the knowledge distillation paradigm. However, instead of obtaining the teacher distribution from a sophisticated MT model, we construct it from a non-parametric datastore via k-Nearest-Neighbor (kNN) retrieval, which removes the dependence on transcription and MT model. Then we decouple the classic knowledge distillation loss into target and non-target distillation to enhance the effect of the knowledge among non-target logits, which is the prominent "dark knowledge". Experiments on MuST-C corpus show that, the proposed method can achieve consistent improvement over the strong baseline without requiring any transcription.