Low-Resource Speech-to-Text Translation

Sameer Bansal, Herman Kamper, Karen Livescu, Adam Lopez, Sharon Goldwater

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Speech-to-text translation has many potential applications for low-resource languages, but the typical approach of cascading speech recognition with machine translation is often impossible, since the transcripts needed to train a speech recognizer are usually not available for low-resource languages. Recent work has found that neural encoder-decoder models can learn to directly translate foreign speech in high-resource scenarios, without the need for intermediate transcription. We investigate whether this approach also works in settings where both data and computation are limited. To make the approach efficient, we make several architectural changes, including a change from character-level to word-level decoding. We find that this choice yields crucial speed improvements that allow us to train with fewer computational resources, yet still performs well on frequent words. We explore models trained on between 20 and 160 hours of data, and find that although models trained on less data have considerably lower BLEU scores, they can still predict words with relatively high precision and recall—around 50% for a model trained on 50 hours of data, versus around 60% for the full 160 hour model. Thus, they may still be useful for some low-resource scenarios.
Index Terms: speech translation, low-resource speech processing, encoder-decoder models
Original languageEnglish
Title of host publicationProceedings of Interspeech 2018
Place of PublicationHyderabad, India
PublisherISCA
Pages1298-1302
Number of pages5
DOIs
Publication statusPublished - 2018
EventInterspeech 2018 - Hyderabad International Convention Centre, Hyderabad, India
Duration: 2 Sep 20186 Sep 2018
http://interspeech2018.org/

Publication series

NameProc. Interspeech 2018
PublisherISCA
ISSN (Electronic)1990-9772

Conference

ConferenceInterspeech 2018
CountryIndia
CityHyderabad
Period2/09/186/09/18
Internet address

Fingerprint

Dive into the research topics of 'Low-Resource Speech-to-Text Translation'. Together they form a unique fingerprint.

Cite this