# Investigating Target Set Reduction for End-to-End Speech Recognition of Hindi-English Code-Switching Data

## TL;DR

This paper proposes a method to reduce target labels in end-to-end speech recognition systems to improve training on limited Hindi-English code-switching data, demonstrating effectiveness on CTC and attention-based models.

## Contribution

It introduces a target set reduction technique specifically designed for code-switching speech recognition, addressing data scarcity and target set expansion issues.

## Key findings

- Reduced target set improves model training with limited data
- Proposed approach outperforms full target set models
- Effective on both CTC and attention-based architectures

## Abstract

End-to-end (E2E) systems are fast replacing the conventional systems in the domain of automatic speech recognition. As the target labels are learned directly from speech data, the E2E systems need a bigger corpus for effective training. In the context of code-switching task, the E2E systems face two challenges: (i) the expansion of the target set due to multiple languages involved, and (ii) the lack of availability of sufficiently large domain-specific corpus. Towards addressing those challenges, we propose an approach for reducing the number of target labels for reliable training of the E2E systems on limited data. The efficacy of the proposed approach has been demonstrated on two prominent architectures, namely CTC-based and attention-based E2E networks. The experimental validations are performed on a recently created Hindi-English code-switching corpus. For contrast purpose, the results for the full target set based E2E system and a hybrid DNN-HMM system are also reported.