Efficient CTC Regularization via Coarse Labels for End-to-End Speech Translation

TL;DR

This paper introduces CoLaCTC, a method that simplifies CTC label space for end-to-end speech translation, significantly improving training efficiency while maintaining or enhancing translation quality.

Contribution

It proposes coarse labeling strategies for CTC, reducing computational overhead and model complexity without sacrificing translation performance.

Findings

CoLaCTC compresses label space to 256 labels or fewer.

Achieves 1.18x to 1.77x training speedup.

Maintains or improves translation quality across multiple languages.

Abstract

For end-to-end speech translation, regularizing the encoder with the Connectionist Temporal Classification (CTC) objective using the source transcript or target translation as labels can greatly improve quality metrics. However, CTC demands an extra prediction layer over the vocabulary space, bringing in nonnegligible model parameters and computational overheads, although this layer is typically not used for inference. In this paper, we re-examine the need for genuine vocabulary labels for CTC for regularization and explore strategies to reduce the CTC label space, targeting improved efficiency without quality degradation. We propose coarse labeling for CTC (CoLaCTC), which merges vocabulary labels via simple heuristic rules, such as using truncation, division or modulo (MOD) operations. Despite its simplicity, our experiments on 4 source and 8 target languages show that CoLaCTC with MOD particularly can compress the label space aggressively to 256 and even further, gaining training efficiency (1.18x ~ 1.77x speedup depending on the original vocabulary size) yet still delivering comparable or better performance than the CTC baseline. We also show that CoLaCTC successfully generalizes to CTC regularization regardless of using transcript or translation for labeling.