Custom Data Augmentation for low resource ASR using Bark and Retrieval-Based Voice Conversion
Not on the map. Why?
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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 10 of its 15 references that are in the map. First posted on arXiv 24 Nov 2023.
Builds on
10 of 15 references.
References · 10
- 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
- 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
- 2017Tacotron: Towards End-to-End Speech Synthesiscited by 487
- 2020FastPitch: Parallel Text-to-speech with Pitch Predictioncited by 150
- 2021End-to-end speaker segmentation for overlap-aware resegmentationcited by 76
- 2023Better speech synthesis through scalingcited by 63
- 2021LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Searchcited by 27
- 2020Low-resource expressive text-to-speech using data augmentationcited by 26
- 2018Effect of data reduction on sequence-to-sequence neural TTScited by 16
- 2019Training Multi-Speaker Neural Text-to-Speech Systems using Speaker-Imbalanced Speech Corporacited by 8
Built on by
Citing papers per year: 2025: 3.
3 papers.