Leveraging Zipformer Model for Effective Language Identification in Code-Switched Child-Directed Speech
This addresses language identification challenges in bilingual child-directed speech, representing an incremental improvement with specific gains.
The paper tackled language identification in code-switched child-directed speech by using Zipformer to handle imbalanced Mandarin-English data, achieving a Balanced Accuracy of 81.89%, a 15.47% improvement over the baseline.
Code-switching and language identification in child-directed scenarios present significant challenges, particularly in bilingual environments. This paper addresses this challenge by using Zipformer to handle the nuances of speech, which contains two imbalanced languages, Mandarin and English, in an utterance. This work demonstrates that the internal layers of the Zipformer effectively encode the language characteristics, which can be leveraged in language identification. We present the selection methodology of the inner layers to extract the embeddings and make a comparison with different back-ends. Our analysis shows that Zipformer is robust across these backends. Our approach effectively handles imbalanced data, achieving a Balanced Accuracy (BAC) of 81.89%, a 15.47% improvement over the language identification baseline. These findings highlight the potential of the transformer encoder architecture model in real scenarios.