On Using SpecAugment for End-to-End Speech Translation

descriptionPublicationkeyboard_double_arrow_right Conference object , Article , Preprint 01 Jan 2019Embargo end date: 01 Nov 2019Publisher:ZenodoJournal:CoRR, volume abs/1911.08876Funded by:EC | SEQCLAS

Authors: Parnia Bahar; Albert Zeyer; Ralf Schlüter; Hermann Ney;

doi: 10.5281/zenodo.3525009 , 10.5281/zenodo.3525010 , 10.48550/arxiv.1911.08876

arXiv: 1911.08876

On Using SpecAugment for End-to-End Speech Translation

- Summary
- Subjects
- Metrics

Abstract

This work investigates a simple data augmentation technique, SpecAugment, for end-to-end speech translation. SpecAugment is a low-cost implementation method applied directly to the audio input features and it consists of masking blocks of frequency channels, and/or time steps. We apply SpecAugment on end-to-end speech translation tasks and achieve up to +2.2\% \BLEU on LibriSpeech Audiobooks En->Fr and +1.2% on IWSLT TED-talks En->De by alleviating overfitting to some extent. We also examine the effectiveness of the method in a variety of data scenarios and show that the method also leads to significant improvements in various data conditions irrespective of the amount of training data.

8 pages, International Workshop on Spoken Language Translation (IWSLT), Hong Kong, China, November 2019

Related Organizations

RWTH Aachen University
Germany
RWTH Aachen University (Medical Faculty)
Germany

Keywords

FOS: Computer and information sciences, Computer Science - Machine Learning, Computer Science - Computation and Language, Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, Computation and Language (cs.CL), Electrical Engineering and Systems Science - Audio and Speech Processing, Machine Learning (cs.LG)

Impact byBIP!

	citations The total number of citations received by all articles of the researcher of interest.	20
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average