# Leveraging Zipformer Model for Effective Language Identification in Code-Switched Child-Directed Speech

arXiv: https://arxiv.org/abs/2508.09430 · HTML: https://mlsanity.com/paper/2508.09430/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 22 references that are in the map.
- First posted on arXiv 13 Aug 2025.

## Builds on (most cited first, 10 of 10)

- [AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale](https://mlsanity.com/paper/1808.10583/) (2018)
- [Zipformer: A faster and better encoder for automatic speech recognition](https://mlsanity.com/paper/2310.11230/) (2023)
- [Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems](https://mlsanity.com/paper/1709.04482/) (2017)
- [TALCS: An Open-Source Mandarin-English Code-Switching Corpus and a Speech Recognition Baseline](https://mlsanity.com/paper/2206.13135/) (2022)
- [MERLIon CCS Challenge: A English-Mandarin code-switching child-directed speech corpus for language identification and diarization](https://mlsanity.com/paper/2305.18881/) (2023)
- [Understanding the effects of language-specific class imbalance in multilingual fine-tuning](https://mlsanity.com/paper/2402.13016/) (2024)
- [Accidental Learners: Spoken Language Identification in Multilingual Self-Supervised Models](https://mlsanity.com/paper/2211.05103/) (2022)
- [Simple yet Effective Code-Switching Language Identification with Multitask Pre-Training and Transfer Learning](https://mlsanity.com/paper/2305.19759/) (2023)
- [Spoken Language Identification System for English-Mandarin Code-Switching Child-Directed Speech](https://mlsanity.com/paper/2306.00736/) (2023)
- [Generative linguistic representation for spoken language identification](https://mlsanity.com/paper/2312.10964/) (2023)

## Abstract (arXiv)

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.