Pith. sign in

REVIEW

Word-level Speech Recognition with a Letter to Word Encoder

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 1906.04323 v2 pith:WFEX3WLZ submitted 2019-06-10 cs.CL cs.SDeess.AS

classification cs.CLcs.SDeess.AS
keywords modelworddirect-to-wordmodelslevelnetworkrecognitionsequence
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose a direct-to-word sequence model which uses a word network to learn word embeddings from letters. The word network can be integrated seamlessly with arbitrary sequence models including Connectionist Temporal Classification and encoder-decoder models with attention. We show our direct-to-word model can achieve word error rate gains over sub-word level models for speech recognition. We also show that our direct-to-word approach retains the ability to predict words not seen at training time without any retraining. Finally, we demonstrate that a word-level model can use a larger stride than a sub-word level model while maintaining accuracy. This makes the model more efficient both for training and inference.

Discussion (0). Sign in to comment.

Pith tools