Pith. sign in

REVIEW

Phone Features Improve Speech Translation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2005.13681 v1 pith:GPBH5W7U submitted 2020-05-27 cs.CL cs.SDeess.AS

Phone Features Improve Speech Translation

classification cs.CL cs.SDeess.AS
keywords modelsend-to-endfeaturesspeechtranslationarchitecturescascadesconditions
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

End-to-end models for speech translation (ST) more tightly couple speech recognition (ASR) and machine translation (MT) than a traditional cascade of separate ASR and MT models, with simpler model architectures and the potential for reduced error propagation. Their performance is often assumed to be superior, though in many conditions this is not yet the case. We compare cascaded and end-to-end models across high, medium, and low-resource conditions, and show that cascades remain stronger baselines. Further, we introduce two methods to incorporate phone features into ST models. We show that these features improve both architectures, closing the gap between end-to-end models and cascades, and outperforming previous academic work -- by up to 9 BLEU on our low-resource setting.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.