# Balanced End-to-End Monolingual pre-training for Low-Resourced Indic Languages Code-Switching Speech Recognition

arXiv: https://arxiv.org/abs/2106.05885 · HTML: https://mlsanity.com/paper/2106.05885/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 26 references that are in the map.
- First posted on arXiv 10 Jun 2021.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning](https://mlsanity.com/paper/1609.06773/) (2016)
- [TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation](https://mlsanity.com/paper/1805.04699/) (2018)
- [Recent Developments on ESPnet Toolkit Boosted by Conformer](https://mlsanity.com/paper/2010.13956/) (2020)
- [Multilingual Speech Recognition With A Single End-To-End Model](https://mlsanity.com/paper/1711.01694/) (2017)
- [A Survey of Code-switched Speech and Language Processing](https://mlsanity.com/paper/1904.00784/) (2019)
- [Towards One Model to Rule All: Multilingual Strategy for Dialectal Code-Switching Arabic ASR](https://mlsanity.com/paper/2105.14779/) (2021)
- [Multi-Encoder-Decoder Transformer for Code-Switching Speech Recognition](https://mlsanity.com/paper/2006.10414/) (2020)
- [Towards End-to-End Code-Switching Speech Recognition](https://mlsanity.com/paper/1810.13091/) (2018)
- [Language-agnostic Multilingual Modeling](https://mlsanity.com/paper/2004.09571/) (2020)

## Built on by (most cited first, 1 of 1)

- [Speech collage: code-switched audio generation by collaging monolingual corpora](https://mlsanity.com/paper/2309.15674/) (2023)

## Abstract (arXiv)

The success in designing Code-Switching (CS) ASR often depends on the availability of the transcribed CS resources. Such dependency harms the development of ASR in low-resourced languages such as Bengali and Hindi. In this paper, we exploit the transfer learning approach to design End-to-End (E2E) CS ASR systems for the two low-resourced language pairs using different monolingual speech data and a small set of noisy CS data. We trained the CS-ASR, following two steps: (i) building a robust bilingual ASR system using a convolution-augmented transformer (Conformer) based acoustic model and n-gram language model, and (ii) fine-tuned the entire E2E ASR with limited noisy CS data. We tested our method on MUCS 2021 challenge and achieved 3rd place in the CS track. We then tested the proposed method using noisy CS data released for Hindi-English and Bengali-English pairs in Multilingual and Code-Switching ASR Challenges for Low Resource Indian Languages (MUCS 2021) and achieved 3rd place in the CS track. Unlike, the leading two systems that benefited from crawling YouTube and learning transliteration pairs, our proposed transfer learning approach focused on using only the limited CS data with no data-cleaning or data re-segmentation. Our approach achieved 14.1% relative gain in word error rate (WER) in Hindi-English and 27.1% in Bengali-English. We provide detailed guidelines on the steps to finetune the self-attention based model for limited data for ASR. Moreover, we release the code and recipe used in this paper.