DeepAI
Log In Sign Up

A bandit approach to curriculum generation for automatic speech recognition

02/06/2021
by   Anastasia Kuznetsova, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

02/17/2022

Curriculum optimization for low-resource speech recognition

Modern end-to-end speech recognition models show astonishing results in ...
06/01/2022

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

Automatic Speech Recognition (ASR) has increasing utility in the modern ...
10/11/2022

Automatic Speech Recognition of Low-Resource Languages Based on Chukchi

The following paper presents a project focused on the research and creat...
08/10/2022

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...
04/07/2019

On The Power of Curriculum Learning in Training Deep Networks

Training neural networks is traditionally done by providing a sequence o...
11/09/2016

Incremental Sequence Learning

Deep learning research over the past years has shown that by increasing ...
12/22/2020

Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition

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