# Language-agnostic Multilingual Modeling

arXiv: https://arxiv.org/abs/2004.09571 · HTML: https://mlsanity.com/paper/2004.09571/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Apr 2020.

## Built on by (most cited first, 17 of 17)

- [Language Models are Few-shot Multilingual Learners](https://mlsanity.com/paper/2109.07684/) (2021)
- [Multilingual and code-switching ASR challenges for low resource Indian languages](https://mlsanity.com/paper/2104.00235/) (2021)
- [Towards One Model to Rule All: Multilingual Strategy for Dialectal Code-Switching Arabic ASR](https://mlsanity.com/paper/2105.14779/) (2021)
- [Exploiting Adapters for Cross-lingual Low-resource Speech Recognition](https://mlsanity.com/paper/2105.11905/) (2021)
- [Arabic Code-Switching Speech Recognition using Monolingual Data](https://mlsanity.com/paper/2107.01573/) (2021)
- [Maestro-U: Leveraging joint speech-text representation learning for zero supervised speech ASR](https://mlsanity.com/paper/2210.10027/) (2022)
- [Automatic Pronunciation Assessment -- A Review](https://mlsanity.com/paper/2310.13974/) (2023)
- [Continual Learning Optimizations for Auto-regressive Decoder of Multilingual ASR systems](https://mlsanity.com/paper/2407.03645/) (2024)
- [Dual Script E2E framework for Multilingual and Code-Switching ASR](https://mlsanity.com/paper/2106.01400/) (2021)
- [Code-Switching in End-to-End Automatic Speech Recognition: A Systematic Literature Review](https://mlsanity.com/paper/2507.07741/) (2025)
- [Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of A Multilingual ASR Model](https://mlsanity.com/paper/2309.13018/) (2023)
- [LangSAMP: Language-Script Aware Multilingual Pretraining](https://mlsanity.com/paper/2409.18199/) (2024)
- [Balanced End-to-End Monolingual pre-training for Low-Resourced Indic Languages Code-Switching Speech Recognition](https://mlsanity.com/paper/2106.05885/) (2021)
- [DuDe: Dual-Decoder Multilingual ASR for Indian Languages using Common Label Set](https://mlsanity.com/paper/2210.16739/) (2022)
- [Learning Cross-lingual Mappings for Data Augmentation to Improve Low-Resource Speech Recognition](https://mlsanity.com/paper/2306.08577/) (2023)
- [WavFT: Acoustic model finetuning with labelled and unlabelled data](https://mlsanity.com/paper/2204.00348/) (2022)
- [Are you speaking my languages? On spoken language adherence in multimodal LLMs](https://mlsanity.com/paper/2606.17281/) (2026)

## Abstract (arXiv)

Multilingual Automated Speech Recognition (ASR) systems allow for the joint training of data-rich and data-scarce languages in a single model. This enables data and parameter sharing across languages, which is especially beneficial for the data-scarce languages. However, most state-of-the-art multilingual models require the encoding of language information and therefore are not as flexible or scalable when expanding to newer languages. Language-independent multilingual models help to address this issue, and are also better suited for multicultural societies where several languages are frequently used together (but often rendered with different writing systems). In this paper, we propose a new approach to building a language-agnostic multilingual ASR system which transforms all languages to one writing system through a many-to-one transliteration transducer. Thus, similar sounding acoustics are mapped to a single, canonical target sequence of graphemes, effectively separating the modeling and rendering problems. We show with four Indic languages, namely, Hindi, Bengali, Tamil and Kannada, that the language-agnostic multilingual model achieves up to 10% relative reduction in Word Error Rate (WER) over a language-dependent multilingual model.