Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translation
(2105.04840)Abstract
We study the possibilities of building a non-autoregressive speech-to-text translation model using connectionist temporal classification (CTC), and use CTC-based automatic speech recognition as an auxiliary task to improve the performance. CTC's success on translation is counter-intuitive due to its monotonicity assumption, so we analyze its reordering capability. Kendall's tau distance is introduced as the quantitative metric, and gradient-based visualization provides an intuitive way to take a closer look into the model. Our analysis shows that transformer encoders have the ability to change the word order and points out the future research direction that worth being explored more on non-autoregressive speech translation.
We're not able to analyze this paper right now due to high demand.
Please check back later (sorry!).
Generate a summary of this paper on our Pro plan:
We ran into a problem analyzing this paper.