# LASE: Language-Adversarial Speaker Encoding for Indic Cross-Script Identity Preservation

arXiv: https://arxiv.org/abs/2605.00777 · HTML: https://mlsanity.com/paper/2605.00777/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 1 May 2026.

## Builds on (most cited first, 9 of 9)

- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [Why does Self-Supervised Learning for Speech Recognition Benefit Speaker Recognition?](https://mlsanity.com/paper/2204.12765/) (2022)
- [Praxy Voice: Voice-Prompt Recovery + BUPS for Commercial-Class Indic TTS from a Frozen Non-Indic Base at Zero Commercial-Training-Data Cost](https://mlsanity.com/paper/2604.25441/) (2026)
- [PSP: An Interpretable Per-Dimension Accent Benchmark for Indic Text-to-Speech](https://mlsanity.com/paper/2604.25476/) (2026)

## Abstract (arXiv)

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.