mlsanityData to 7 Oct 2026

Analysis of Data Augmentation Methods for Low-Resource Maltese ASR

arXiv 2111.07793 ↗First posted 15 Nov 2021cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent years have seen an increased interest in the computational speech processing of Maltese, but resources remain sparse. In this paper, we consider data augmentation techniques for improving speech recognition for low-resource languages, focusing on Maltese as a test case. We consider three different types of data augmentation: unsupervised training, multilingual training and the use of synthesized speech as training data. The goal is to determine which of these techniques, or combination of them, is the most effective to improve speech recognition for languages where the starting point is a small corpus of approximately 7 hours of transcribed speech. Our results show that combining the data augmentation techniques studied here lead us to an absolute WER improvement of 15% without the use of a language model.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 60 references that are in the map. First posted on arXiv 15 Nov 2021.

Builds on

18 of 60 references.

References · 18

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  5. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  6. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  7. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 789
  8. 2021Quality at a Glance: An Audit of Web-Crawled Multilingual Datasetscited by 241
  9. 2019NeMo: a toolkit for building AI applications using Neural Modulescited by 230
  10. 2020Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameterscited by 110
  11. 2019Jasper: An End-to-End Convolutional Neural Acoustic Modelcited by 75
  12. 2019Speech Recognition with Augmented Synthesized Speechcited by 60
6 more
  1. 2017Listening while Speaking: Speech Chain by Deep Learningcited by 46
  2. 2019Generating Synthetic Audio Data for Attention-Based Speech Recognition Systemscited by 46
  3. 2020Improving Cross-Lingual Transfer Learning for End-to-End Speech Recognition with Speech Translationcited by 14
  4. 2018Acoustic and Textual Data Augmentation for Improved ASR of Code-Switching Speechcited by 12
  5. 2020MASRI-HEADSET: A Maltese Corpus for Speech Recognitioncited by 4
  6. 2017Morphological Analysis for the Maltese Language: The Challenges of a Hybrid Systemcited by 2

Built on by

Not cited yet.