# Code-Switching Detection via Language-Selective Dimensions in Speech Foundation Models

arXiv: https://arxiv.org/abs/2610.18726 · HTML: https://mlsanity.com/paper/2610.18726/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 23 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Builds on (most cited first, 19 of 19)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [mHuBERT-147: A Compact Multilingual HuBERT Model](https://mlsanity.com/paper/2406.06371/) (2024)
- [Multilingual and code-switching ASR challenges for low resource Indian languages](https://mlsanity.com/paper/2104.00235/) (2021)
- [Probing phoneme, language and speaker information in unsupervised speech representations](https://mlsanity.com/paper/2203.16193/) (2022)
- [Aligning Speech to Languages to Enhance Code-switching Speech Recognition](https://mlsanity.com/paper/2403.05887/) (2024)
- [CS-FLEURS: A Massively Multilingual and Code-Switched Speech Dataset](https://mlsanity.com/paper/2509.14161/) (2025)
- [Speech collage: code-switched audio generation by collaging monolingual corpora](https://mlsanity.com/paper/2309.15674/) (2023)
- [DISPLACE Challenge: DIarization of SPeaker and LAnguage in Conversational Environments](https://mlsanity.com/paper/2303.00830/) (2023)
- [Exploiting Spectral Augmentation for Code-Switched Spoken Language Identification](https://mlsanity.com/paper/2010.07130/) (2020)
- [The Second DISPLACE Challenge : DIarization of SPeaker and LAnguage in Conversational Environments](https://mlsanity.com/paper/2406.09494/) (2024)
- [Fine-Tuned Self-Supervised Speech Representations for Language Diarization in Multilingual Code-Switched Speech](https://mlsanity.com/paper/2312.09645/) (2023)
- [Simple yet Effective Code-Switching Language Identification with Multitask Pre-Training and Transfer Learning](https://mlsanity.com/paper/2305.19759/) (2023)
- [TalTech-IRIT-LIS Speaker and Language Diarization Systems for DISPLACE 2024](https://mlsanity.com/paper/2407.12743/) (2024)
- [AsyncSwitch: Asynchronous Text-Speech Adaptation for Code-Switched ASR](https://mlsanity.com/paper/2506.14190/) (2025)
- [Improving Code-Switching Speech Recognition with TTS Data Augmentation](https://mlsanity.com/paper/2601.00935/) (2026)
- [CS-YODAS: A Mined Dataset of In-the-Wild Code-Switched Speech](https://mlsanity.com/paper/2606.11514/) (2026)
- [Implicit Self-supervised Language Representation for Spoken Language Diarization](https://mlsanity.com/paper/2308.10470/) (2023)

## Abstract (arXiv)

Code-switching (CS), the alternation between languages within an utterance, is common in multilingual speech but underrepresented in pretraining corpora. Increasing CS coverage requires finding relevant utterances in large speech collections so that they can be included in training data. One way to find such utterances is to transcribe the speech and detect language alternation in the text, but this depends on obtaining accurate multilingual transcriptions. We propose a lightweight method that detects CS directly from speech. It uses frame-level language information in pretrained speech encoders to determine whether both languages are present within an utterance. Specifically, we identify language-selective hidden-state dimensions using monolingual recordings and aggregate their frame-level activations into a CS prediction. With a small CS set used to tune a decision rule, we show that the Whisper-small encoder achieves a mean F1 of 0.798 across 14 language pairs in CS-FLEURS, compared with 0.776 for a CNN and 0.751 for a HuBERT linear baseline trained for monolingual language identification. Our findings suggest that pretrained speech encoders already encode the information needed to identify CS utterances, and they provide a lightweight tool for building more representative multilingual corpora.