mlsanityData to 14 Oct 2026

Data Augmentation for Low-Resource Quechua ASR Improvement

arXiv 2207.06872 ↗First posted 14 Jul 2022cs.SD cs.CL eess.AScited by 9

Not on the map. Why?

Abstract (arXiv)

Automatic Speech Recognition (ASR) is a key element in new services that helps users to interact with an automated system. Deep learning methods have made it possible to deploy systems with word error rates below 5% for ASR of English. However, the use of these methods is only available for languages with hundreds or thousands of hours of audio and their corresponding transcriptions. For the so-called low-resource languages to speed up the availability of resources that can improve the performance of their ASR systems, methods of creating new resources on the basis of existing ones are being investigated. In this paper we describe our data augmentation approach to improve the results of ASR models for low-resource and agglutinative languages. We carry out experiments developing an ASR for Quechua using the wav2letter++ model. We reduced WER by 8.73% through our approach to the base model. The resulting ASR model obtained 22.75% WER and was trained with 99 hours of original resources and 99 hours of synthetic data obtained with a combination of text augmentation and synthetic speech generati

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 14 of its 31 references that are in the map. First posted on arXiv 14 Jul 2022.

Builds on

14 of 31 references.

References · 14

  1. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,380
  2. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,026
  3. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 807
  4. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 804
  5. 2017Tacotron: Towards End-to-End Speech Synthesiscited by 490
  6. 2021ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biasescited by 484
  7. 2015Deep Speech 2: End-to-End Speech Recognition in English and Mandarincited by 451
  8. 2017OpenNMT: Open-source Toolkit for Neural Machine Translationcited by 251
  9. 2018Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relationscited by 201
  10. 2018QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehensioncited by 164
  11. 2019End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architecturescited by 120
  12. 2019Transformer-based Acoustic Modeling for Hybrid Speech Recognitioncited by 88
2 more
  1. 2018Sequence-to-Sequence Data Augmentation for Dialogue Language Understandingcited by 68
  2. 2019Improving RNN Transducer Modeling for End-to-End Speech Recognitioncited by 68

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 4; 2026: 3.

9 papers.

  1. 2025Better Pseudo-labeling with Multi-ASR Fusion and Error Correction by SpeechLLMcited by 6
  2. 2023Text Generation with Speech Synthesis for ASR Data Augmentationcited by 5
  3. 2025An Exhaustive Evaluation of TTS- and VC-based Data Augmentation for ASRcited by 5
  4. 2025Frustratingly Easy Data Augmentation for Low-Resource ASRcited by 3
  5. 2024Automatic Speech Recognition Advancements for Indigenous Languages of the Americascited by 1
  6. 2025Indigenous Languages Spoken in Argentina: A Survey of NLP and Speech Resourcescited by 0
  7. 2026Giving Voice to the Constitution: Low-Resource Text-to-Speech for Quechua and Spanish Using a Bilingual Legal Corpuscited by 0
  8. 2026LuxSQA: Ask Me in Luxembourgish with TTS-Augmented Spoken Question Answeringcited by 0
  9. 2026Error Rate is Not Enough: Costs of Augmentation in Low-Resource ASRcited by 0