Spoken language change detection inspired by speaker change detection

TL;DR

This paper proposes a language change detection system inspired by speaker change detection, utilizing longer analysis windows and prior language knowledge, resulting in significant performance improvements on code-switched speech datasets.

Contribution

The study adapts speaker change detection techniques for language change detection, incorporating longer analysis windows and language priors, and demonstrates substantial performance gains.

Findings

Increased analysis window length improves detection accuracy.

Prior language knowledge significantly enhances performance.

Performance varies between synthetic and real datasets due to segment duration differences.

Abstract

Spoken language change detection (LCD) refers to identifying the language transitions in a code-switched utterance. Similarly, identifying the speaker transitions in a multispeaker utterance is known as speaker change detection (SCD). Since tasks-wise both are similar, the architecture/framework developed for the SCD task may be suitable for the LCD task. Hence, the aim of the present work is to develop LCD systems inspired by SCD. Initially, both LCD and SCD are performed by humans. The study suggests humans require (a) a larger duration around the change point and (b) language-specific prior exposure, for performing LCD as compared to SCD. The larger duration requirement is incorporated by increasing the analysis window length of the unsupervised distance-based approach. This leads to a relative performance improvement of 29.1% and 2.4%, and a priori language knowledge provides a relative improvement of 31.63% and 14.27% on the synthetic and practical codeswitched datasets, respectively. The performance difference between the practical and synthetic datasets is mostly due to differences in the distribution of the monolingual segment duration.