Metraipolis › archive › dc_70144cb45fc6
Zero-Shot Voice Cloning for Synthetic Data Augmentation in Children's ASR — arXiv:2611.03050
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.03050
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T19:09:16.189Z
- SHA-256 of the archived text
dc05ef49fef7f548ce23326d2f909d6cffc3cced111c9fcb9f32d39573780906- Stable URL of this page
https://metraipolis.com/documento/dc_70144cb45fc6
How to cite
Zero-Shot Voice Cloning for Synthetic Data Augmentation in Children's ASR — arXiv:2611.03050 — arXiv (en), https://arxiv.org/abs/2611.03050 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_70144cb45fc6 (Metraipolis archive dc_70144cb45fc6, sha256 dc05ef49fef7f548ce23326d2f909d6cffc3cced111c9fcb9f32d39573780906)
BibTeX
@misc{dc70144cb45fc6,
title = {Zero-Shot Voice Cloning for Synthetic Data Augmentation in Children's ASR — arXiv:2611.03050},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.03050},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_70144cb45fc6; sha256 dc05ef49fef7f548ce23326d2f909d6cffc3cced111c9fcb9f32d39573780906},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03050. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Children's automatic speech recognition (ASR) lags behind adult ASR due to theacoustic mismatch between adult-trained acoustic models and children's speech, as well as the scarcity of labelled children's speech corpora. We investigate whether zero-shot text-to-speech (TTS) synthesis with voice cloning, requiring only a short reference clip per speaker, can serve as a practical substitute for real children's speech when fine-tuning large pre-trained ASR models. Using the OmniVoice multilingual TTS system we synthesise up to 16,000 child-like utterances from two English corpora (ENNI, clinical narrative samples, ages 7-12, and MyST, conversational science-tutor speech, grades 3-5) and fine-tune Whisper-small under different experimental conditions covering real data, synthetic data, cross-corpus data, and all-data combination. A systematic sensitivity analysis over speaker count, text-pool size, and utterances per speaker reveals that synthetic data alone reduces word error rate (WER) from a 19.8 % zero-shot baseline to 16.4 % on ENNI, recovering approximately 30 % of the gap to real-data fine-tuning (8.8 %). Combining synthetic with real data is essentially indistinguishable from real-data-only fine-tuning (9.2 % vs. 8.8 %). Speaker count plateaus at ~40 speakers for cross-domain transfer, while multi-speaker acoustic diversity per transcript, rather than raw text coverage, emerges as the primary determinant of cross-domain generalisation; out-of-vocabulary (OOV) rate proves to be a poor proxy for WER given Whisper's pre-trained language modelling capacity. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv eess.AS, nuovi lavori del giorno). Categorie arXiv: Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2611.03050 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T18:26:07.768Z dalla pagina https://arxiv.org/list/eess.AS/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).