Log In Sign Up

Leveraging translations for speech transcription in low-resource settings

by   Antonis Anastasopoulos, et al.

Recently proposed data collection frameworks for endangered language documentation aim not only to collect speech in the language of interest, but also to collect translations into a high-resource language that will render the collected resource interpretable. We focus on this scenario and explore whether we can improve transcription quality under these extremely low-resource settings with the assistance of text translations. We present a neural multi-source model and evaluate several variations of it on three low-resource datasets. We find that our multi-source model with shared attention outperforms the baselines, reducing transcription character error rate by up to 12.3


page 1

page 2

page 3

page 4


When Is TTS Augmentation Through a Pivot Language Useful?

Developing Automatic Speech Recognition (ASR) for low-resource languages...

High-Resource Methodological Bias in Low-Resource Investigations

The central bottleneck for low-resource NLP is typically regarded to be ...

Learnings from Technological Interventions in a Low Resource Language: Enhancing Information Access in Gondi

The primary obstacle to developing technologies for low-resource languag...

Unsung Challenges of Building and Deploying Language Technologies for Low Resource Language Communities

In this paper, we examine and analyze the challenges associated with dev...

CUNI System for the Building Educational Applications 2019 Shared Task: Grammatical Error Correction

In this paper, we describe our systems submitted to the Building Educati...

SANTLR: Speech Annotation Toolkit for Low Resource Languages

While low resource speech recognition has attracted a lot of attention f...