Log In Sign Up

A bandit approach to curriculum generation for automatic speech recognition

by   Anastasia Kuznetsova, et al.

The Automated Speech Recognition (ASR) task has been a challenging domain especially for low data scenarios with few audio examples. This is the main problem in training ASR systems on the data from low-resource or marginalized languages. In this paper we present an approach to mitigate the lack of training data by employing Automated Curriculum Learning in combination with an adversarial bandit approach inspired by Reinforcement learning. The goal of the approach is to optimize the training sequence of mini-batches ranked by the level of difficulty and compare the ASR performance metrics against the random training sequence and discrete curriculum. We test our approach on a truly low-resource language and show that the bandit framework has a good improvement over the baseline transfer-learning model.


page 1

page 2

page 3

page 4


Curriculum optimization for low-resource speech recognition

Modern end-to-end speech recognition models show astonishing results in ...

Snow Mountain: Dataset of Audio Recordings of The Bible in Low Resource Languages

Automatic Speech Recognition (ASR) has increasing utility in the modern ...

Automatic Speech Recognition of Low-Resource Languages Based on Chukchi

The following paper presents a project focused on the research and creat...

Comparison and Analysis of New Curriculum Criteria for End-to-End ASR

It is common knowledge that the quantity and quality of the training dat...

On The Power of Curriculum Learning in Training Deep Networks

Training neural networks is traditionally done by providing a sequence o...

Incremental Sequence Learning

Deep learning research over the past years has shown that by increasing ...

Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition

Low-resource automatic speech recognition (ASR) is challenging, as the l...