This work focuses on improving the Spoken Language Identification (LangId) system for a challenge that focuses on developing robust language identification systems that are reliable for non-standard, accented (Singaporean accent), spontaneous code-switched, and child-directed speech collected via Zoom. We propose a two-stage Encoder-Decoder-based E2E model. The encoder module consists of 1D depth-wise separable convolutions with Squeeze-and-Excitation (SE) layers with a global context. The decoder module uses an attentive temporal pooling mechanism to get fixed length time-independent feature representation. The total number of parameters in the model is around 22.1 M, which is relatively light compared to using some large-scale pre-trained speech models. We achieved an EER of 15.6% in the closed track and 11.1% in the open track (baseline system 22.1%). We also curated additional LangId data from YouTube videos (having Singaporean speakers), which will be released for public use.

翻译：本研究致力于改进面向一项挑战的口语语种识别（LangId）系统，该挑战聚焦于开发稳健的语种识别系统，能够可靠处理通过Zoom采集的非标准、带口音（新加坡口音）、自发性语码转换及儿童导向语音。我们提出了一种基于编码器-解码器的两阶段端到端（E2E）模型。编码器模块采用一维深度可分离卷积，结合具有全局上下文的Squeeze-and-Excitation（SE）层；解码器模块则使用注意力时序池化机制，获取固定长度的时不变特征表示。模型总参数量约为22.1 M，相较于使用大型预训练语音模型更为轻量。我们在封闭赛道中实现了15.6%的等错误率（EER），开放赛道中达到11.1%（基线系统为22.1%）。此外，我们还从YouTube视频（包含新加坡说话人）中额外整理了LangId数据，这些数据将公开发布供公众使用。