用预训练模型和边界损失提升语音语言识别准确率
Spoken Language Identification with Pre-trained Models and Margin Loss
- 基于ECAPA-TDNN提取特征，结合边界损失增强语言表征区分度
- 在Tidy-X数据集上达到85.95%宏准确率与90.96%微准确率
- 显著降低说话人干扰，适合语音识别与验证场景应用
针对TidyLang Challenge 2026提出的说话人控制语音语言识别任务，本文提出一种基于预训练模型与边界损失的语言识别方法。该方法采用预训练的ECAPA-TDNN作为特征编码器，并引入边界损失以增强语言表征的判别能力，从而提高类间可分性并减少说话人等非语言因素的干扰。在Tidy-X数据集上的实验结果表明，该方法在语言识别任务中取得85.95%的宏准确率和90.96%的微准确率，在验证任务中实现17.08%的等错误率（EER）。相比官方基线，宏准确率提升45.7%，微准确率提升15.2%，EER降低约50.8%，充分验证了方法的有效性。代码将公开于https://github.com/PunkMale/TidyLang2026。
原文摘要 · Abstract (English)
For the speaker-controlled spoken language identification task proposed in the TidyLang Challenge 2026, this paper proposes a language identification method based on pre-trained models and margin-based losses. The proposed method adopts a pre-trained ECAPA-TDNN as the feature encoder and incorporates margin-based losses to enhance the discriminative ability of language representations, thereby improving inter-class separability and reducing the interference of non-linguistic factors such as speaker characteristics. Experimental results on the Tidy-X dataset show that the proposed method achieves 85.95% macro accuracy and 90.96% micro accuracy on the language identification task and 17.08% equal error rate (EER) on the verification task. Compared with the official baseline, the macro accuracy improves by 45.7%, the micro accuracy improves by 15.2%, and the EER is reduced by approximately 50.8%, demonstrating the effectiveness of the proposed method. The code will be released at https://github.com/PunkMale/TidyLang2026.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。