# Joint Language Identification of Code-Switching Speech using Attention based E2E Network

## TL;DR

This paper introduces an attention-based end-to-end model for joint language identification in code-switching speech, demonstrating improved accuracy and boundary detection over traditional methods using a Hindi-English corpus.

## Contribution

It proposes a novel joint modeling approach with an attention-based E2E network for language ID in code-switching speech, outperforming TCR-based models.

## Key findings

- Attention-based E2E model achieves higher accuracy.
- Effective boundary detection shown via attention weights.
- Outperforms TCR-based LID system.

## Abstract

Language identification (LID) has relevance in many speech processing applications. For the automatic recognition of code-switching speech, the conventional approaches often employ an LID system for detecting the languages present within an utterance. In the existing works, the LID on code-switching speech involves modelling of the underlying languages separately. In this work, we propose a joint modelling based LID system for code-switching speech. To achieve the same, an attention-based end-to-end (E2E) network has been explored. For the development and evaluation of the proposed approach, a recently created Hindi-English code-switching corpus has been used. For the contrast purpose, an LID system employing the connectionist temporal classification-based E2E network is also developed. On comparing both the LID systems, the attention based approach is noted to result in better LID accuracy. The effective location of code-switching boundaries within the utterance by the proposed approach has been demonstrated by plotting the attention weights of E2E network.