# Custom Data Augmentation for low resource ASR using Bark and Retrieval-Based Voice Conversion

arXiv: https://arxiv.org/abs/2311.14836 · HTML: https://mlsanity.com/paper/2311.14836/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 15 references that are in the map.
- First posted on arXiv 24 Nov 2023.

## Builds on (most cited first, 10 of 10)

- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [FastPitch: Parallel Text-to-speech with Pitch Prediction](https://mlsanity.com/paper/2006.06873/) (2020)
- [End-to-end speaker segmentation for overlap-aware resegmentation](https://mlsanity.com/paper/2104.04045/) (2021)
- [Better speech synthesis through scaling](https://mlsanity.com/paper/2305.07243/) (2023)
- [LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search](https://mlsanity.com/paper/2102.04040/) (2021)
- [Low-resource expressive text-to-speech using data augmentation](https://mlsanity.com/paper/2011.05707/) (2020)
- [Effect of data reduction on sequence-to-sequence neural TTS](https://mlsanity.com/paper/1811.06315/) (2018)
- [Training Multi-Speaker Neural Text-to-Speech Systems using Speaker-Imbalanced Speech Corpora](https://mlsanity.com/paper/1904.00771/) (2019)

## Built on by (most cited first, 3 of 3)

- [Who Gets the Mic? Investigating Gender Bias in the Speaker Assignment of a Speech-LLM](https://mlsanity.com/paper/2508.13603/) (2025)
- [Improving Low-Resource Dialect Classification Using Retrieval-based Voice Conversion](https://mlsanity.com/paper/2507.03641/) (2025)
- [A Survey on Spoken Italian Datasets and Corpora](https://mlsanity.com/paper/2501.06557/) (2025)

## Abstract (arXiv)

This paper proposes two innovative methodologies to construct customized Common Voice datasets for low-resource languages like Hindi. The first methodology leverages Bark, a transformer-based text-to-audio model developed by Suno, and incorporates Meta's enCodec and a pre-trained HuBert model to enhance Bark's performance. The second methodology employs Retrieval-Based Voice Conversion (RVC) and uses the Ozen toolkit for data preparation. Both methodologies contribute to the advancement of ASR technology and offer valuable insights into addressing the challenges of constructing customized Common Voice datasets for under-resourced languages. Furthermore, they provide a pathway to achieving high-quality, personalized voice generation for a range of applications.