Everyday Speech in the Indian Subcontinent

TL;DR

This paper introduces a phonetics-based Common Label Set (CLS) for multilingual speech synthesis in India, enabling seamless code switching among 13 languages and English, reflecting everyday multilingual speech.

Contribution

It proposes a novel CLS approach that simplifies multilingual synthesis and supports code switching in Indian languages within an E2E framework.

Findings

Enables seamless code switching across 13 Indian languages and English.

Reduces vocabulary complexity in multilingual speech synthesis.

Supports natural everyday speech in multilingual Indian contexts.

Abstract

India has 1369 languages of which 22 are official. About 13 different scripts are used to represent these languages. A Common Label Set (CLS) was developed based on phonetics to address the issue of large vocabulary of units required in the End-to-End (E2E) framework for multilingual synthesis. The Indian language text is first converted to CLS. This approach enables seamless code switching across 13 Indian languages and English in a given native speaker's voice, which corresponds to everyday speech in the Indian subcontinent, where the population is multilingual.