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.

翻译：摘要：用于多语言语音克隆的说话人编码器应同等对待同一说话人，无论其音频使用何种语种。现成的编码器无法做到这一点，且失败表现为口音条件性。在涵盖英语、印地语、泰卢固语和泰米尔语的1043对西式口音语音语料库中，WavLM-base-plus-sv在相同声音改变语种时余弦相似度降低0.082，ECAPA-TDNN降低0.105；在1369对印度口音语音语料库中，差距缩小至0.006（WavLM-SV）和0.044（ECAPA-TDNN）。这种信息泄露在跨语种TTS最关键时最为严重：当系统将非印度语言训练的声音投射至印度语种时。我们提出LASE（语言对抗性说话人编码器），这是一个基于冻结WavLM-base的小型投影头，通过两种损失训练：基于说话人身份的监督对比损失，以及针对4语言分类器的梯度反转交叉熵，该分类器推动嵌入在保持说话人信息的同时不携带语言信息。在来自8个商业多语言声音合成的1118个质量筛选跨语种对上训练后，LASE的残余差距在两个语料库上均与零一致（西式口音Delta=0.013，印度口音Delta=0.026；两者的Bootstrap 95%置信区间均包含零），并将跨语种与底层的边界比基线增强2.4-2.7倍。ECAPA+GRL消融实验表明，GRL目标可改进任一主干网络，但WavLM选择亦有贡献。在合成多说话人日记化任务中，LASE在跨语种说话人召回率上（0.788对比0.789）匹配ECAPA-TDNN，且训练数据量减少约100倍。我们发布r1检查点、两个语料库及Bootstrap方法。