| title | LASE: Language-Adversarial Speaker Encoding for Indic Cross-Script Identity Preservation |
|---|---|
| authors | Venkata Pushpak Teja Menta |
| date | 2026-05-01 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.00777 |
| affiliation | Praxel |
| links | abs pdf hf code |
| abstract | A speaker encoder used in multilingual voice cloning should treat the same speaker identically regardless of which script the audio was uttered in. Off-the-shelf encoders do not, and the failure is accent-conditional. On a 1043-pair Western-accented voice corpus across English, Hindi, Telugu, and Tamil, WavLM-base-plus-sv loses 0.082 absolute cosine similarity when the same voice changes script and ECAPA-TDNN loses 0.105. On a 1369-pair Indian-accented voice corpus, the gap shrinks to 0.006 (WavLM-SV) and 0.044 (ECAPA-TDNN). The leak is largest where it matters most for cross-script TTS: when a system projects a non-Indic-trained voice into Indic scripts. We present LASE (Language-Adversarial Speaker Encoder), a small projection head over frozen WavLM-base-plus trained with two losses: a supervised contrastive loss over voice identity, and a gradient-reversal cross-entropy against a 4-language classifier that pushes the embedding to be language-uninformative while remaining speaker-informative. Trained on 1118 quality-gated cross-script pairs synthesised from 8 commercial multilingual voices, LASE's residual gap is consistent with zero on both corpora (Delta = 0.013 Western, Delta = 0.026 Indian; both bootstrap 95% CIs include zero) and amplifies the cross-script-vs-floor margin 2.4-2.7x over both baselines. An ECAPA+GRL ablation shows the GRL objective improves either backbone but the WavLM choice contributes too. In synthetic multi-speaker diarisation, LASE matches ECAPA-TDNN on cross-script speaker recall (0.788 vs 0.789) with ~100x less training data. We release the r1 checkpoint, both corpora, and the bootstrap recipe. |
cite
@misc{menta2026lase,
title={LASE: Language-Adversarial Speaker Encoding for Indic Cross-Script Identity Preservation},
author={Venkata Pushpak Teja Menta},
year={2026},
eprint={2605.00777},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.00777}
}