The reviewed record of science sign in
Pith

arxiv: 2505.20693 · v1 · pith:6MQSOVE4 · submitted 2025-05-27 · cs.CL · cs.LG· cs.SD· eess.AS

Phir Hera Fairy: An English Fairytaler is a Strong Faker of Fluent Speech in Low-Resource Indian Languages

Praveen Srinivasa Varadhan , Srija Anand , Soma Siddhartha , Mitesh M.Khapra This is my paper

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:6MQSOVE4record.jsonopen to challenge →

classification cs.CL cs.LGcs.SDeess.AS
keywords englishindianlanguagesdatafine-tuninglow-resourcefairytalerin-f5
0
0 comments X
read the original abstract

What happens when an English Fairytaler is fine-tuned on Indian languages? We evaluate how the English F5-TTS model adapts to 11 Indian languages, measuring polyglot fluency, voice-cloning, style-cloning, and code-mixing. We compare: (i) training from scratch, (ii) fine-tuning English F5 on Indian data, and (iii) fine-tuning on both Indian and English data to prevent forgetting. Fine-tuning with only Indian data proves most effective and the resultant IN-F5 is a near-human polyglot; that enables speakers of one language (e.g., Odia) to fluently speak in another (e.g., Hindi). Our results show English pretraining aids low-resource TTS in reaching human parity. To aid progress in other low-resource languages, we study data-constrained setups and arrive at a compute optimal strategy. Finally, we show IN-F5 can synthesize unseen languages like Bhojpuri and Tulu using a human-in-the-loop approach for zero-resource TTS via synthetic data generation.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Preferences of a Voice-First Nation: Large-Scale Pairwise Evaluation and Preference Analysis for TTS in Indian Languages

    cs.CL 2026-04 unverdicted novelty 7.0

    A controlled pairwise evaluation framework for multilingual TTS in 10 Indic languages produces a preference leaderboard using Bradley-Terry modeling and SHAP analysis on 120K+ comparisons.

  2. CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations

    eess.AS 2026-06 unverdicted novelty 5.0

    CrossAccent-TTS adds an Accent Intensity Controller to disentangled representations for controllable accent strength in cross-lingual TTS on Indic and L2 datasets.