Identification/Segmentation of Indian Regional Languages with Singular Value Decomposition based Feature Embedding

TL;DR

This paper explores two SVD-based feature embedding schemes for Indian language identification and segmentation, showing that different schemes perform better depending on test duration and that 55-65% singular value energy captures essential language features.

Contribution

It introduces two novel SVD-based feature embedding schemes for Indian language identification and segmentation, with comparative analysis of their effectiveness.

Findings

Supervector and n-gram schemes capture 55-65% singular value energy.

Supervector scheme performs better on short test signals.

N-gram scheme outperforms on longer test signals.

Abstract

language identification (LID) is identifing a language in a given spoken utterance. Language segmentation is equally inportant as language identification where language boundaries can be spotted in a multi language utterance. In this paper, we have experimented with two schemes for language identification in Indian regional language context as very few works has been done. Singular value based feature embedding is used for both of the schemes. In first scheme, the singular value decomposition (SVD) is applied to the n-gram utterance matrix and in the second scheme, SVD is applied on the difference supervector matrix space. We have observed that in both the schemes, 55-65% singular value energy is sufficient to capture the language context. In n-gram based feature representation, we have seen that different skipgram models capture different language context. We have observed that for short test duration, supervector based feature representation is better but with a longer duration test signal, n-gram based feature performed better. We have also extended our work to explore language-based segmentation where we have seen that segmentation accuracy of four language group with ten language training model, scheme-1 has performed well but with same four language training model, scheme-2 outperformed scheme-1