# SAGE: Spliced-Audio Generated Data for Enhancing Foundational Models in Low-Resource Arabic-English Code-Switched Speech Recognition

arXiv: https://arxiv.org/abs/2506.22143 · HTML: https://mlsanity.com/paper/2506.22143/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 27 Jun 2025.

## Builds on (most cited first, 25 of 25)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Unsupervised Cross-lingual Representation Learning for Speech Recognition](https://mlsanity.com/paper/2006.13979/) (2020)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages](https://mlsanity.com/paper/2303.01037/) (2023)
- [Comparative layer-wise analysis of self-supervised speech models](https://mlsanity.com/paper/2211.03929/) (2022)
- [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)
- [QASR: QCRI Aljazeera Speech Resource -- A Large Scale Annotated Arabic Speech Corpus](https://mlsanity.com/paper/2106.13000/) (2021)
- [Data Augmentation for End-to-end Code-switching Speech Recognition](https://mlsanity.com/paper/2011.02160/) (2020)
- [N-Shot Benchmarking of Whisper on Diverse Arabic Speech Recognition](https://mlsanity.com/paper/2306.02902/) (2023)
- [Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition](https://mlsanity.com/paper/2406.02925/) (2024)
- [Zero Resource Code-switched Speech Benchmark Using Speech Utterance Pairs For Multiple Spoken Languages](https://mlsanity.com/paper/2310.03018/) (2023)
- [Multilingual self-supervised speech representations improve the speech recognition of low-resource African languages with codeswitching](https://mlsanity.com/paper/2311.15077/) (2023)
- [Speech collage: code-switched audio generation by collaging monolingual corpora](https://mlsanity.com/paper/2309.15674/) (2023)
- [ZAEBUC-Spoken: A Multilingual Multidialectal Arabic-English Speech Corpus](https://mlsanity.com/paper/2403.18182/) (2024)
- [Exploring WavLM on Speech Enhancement](https://mlsanity.com/paper/2211.09988/) (2022)
- [Wav2vec-S: Semi-Supervised Pre-Training for Low-Resource ASR](https://mlsanity.com/paper/2110.04484/) (2021)
- [Optimizing Bilingual Neural Transducer with Synthetic Code-switching Text Generation](https://mlsanity.com/paper/2210.12214/) (2022)
- [Progressive unsupervised domain adaptation for ASR using ensemble models and multi-stage training](https://mlsanity.com/paper/2402.04805/) (2024)

## Built on by (most cited first, 2 of 2)

- [Adapting Language Balance in Code-Switching Speech](https://mlsanity.com/paper/2510.18724/) (2025)
- [CTC-DID: CTC-Based Arabic dialect identification for streaming applications](https://mlsanity.com/paper/2601.12199/) (2026)

## Abstract (arXiv)

This paper investigates the performance of various speech SSL models on dialectal Arabic (DA) and Arabic-English code-switched (CS) speech. To address data scarcity, a modified audio-splicing approach is introduced to generate artificial CS speech data. Fine-tuning an already fine-tuned SSL model with the proposed Spliced-Audio Generated (SAGE) data results in an absolute improvement on Word Error Rate (WER) of 7.8% on Arabic and English CS benchmarks. Additionally, an Experience Replay (ER) inspired approach is proposed to enhance generalisation across DA and CS speech while mitigating catastrophic forgetting. Integrating an out-of-domain 3-gram language model reduces the overall mean WER from 31.7% to 26.6%. Few-shot fine-tuning for code-switching benchmarks further improves WER by 4.9%. A WER of 31.1% on Arabic-English CS benchmarks surpasses large-scale multilingual models, including USM and Whisper-large-v2 (both over ten times larger) by an absolute margin of 5.5% and 8.4%, respectively.