Generic Indic Text-to-speech Synthesisers with Rapid Adaptation in an End-to-end Framework

TL;DR

This paper presents a generic end-to-end TTS framework for Indian languages that leverages language family similarities, enabling rapid adaptation to new languages with minimal data and preserving speaker prosody.

Contribution

The work introduces a novel multi-language generic TTS system exploiting language family properties, with effective adaptation to new languages using only 7 minutes of data.

Findings

High-quality TTS with 3.98 MOS after adaptation

Effective language and speaker switching capabilities

Rapid adaptation with minimal data (7 minutes)

Abstract

Building text-to-speech (TTS) synthesisers for Indian languages is a difficult task owing to a large number of active languages. Indian languages can be classified into a finite set of families, prominent among them, Indo-Aryan and Dravidian. The proposed work exploits this property to build a generic TTS system using multiple languages from the same family in an end-to-end framework. Generic systems are quite robust as they are capable of capturing a variety of phonotactics across languages. These systems are then adapted to a new language in the same family using small amounts of adaptation data. Experiments indicate that good quality TTS systems can be built using only 7 minutes of adaptation data. An average degradation mean opinion score of 3.98 is obtained for the adapted TTSes. Extensive analysis of systematic interactions between languages in the generic TTSes is carried out. x-vectors are included as speaker embedding to synthesise text in a particular speaker's voice. An interesting observation is that the prosody of the target speaker's voice is preserved. These results are quite promising as they indicate the capability of generic TTSes to handle speaker and language switching seamlessly, along with the ease of adaptation to a new language.