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

arXiv: https://arxiv.org/abs/2006.06971 · HTML: https://mlsanity.com/paper/2006.06971/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2020.

## Built on by (most cited first, 9 of 9)

- [Towards Building Text-To-Speech Systems for the Next Billion Users](https://mlsanity.com/paper/2211.09536/) (2022)
- [IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS](https://mlsanity.com/paper/2409.05356/) (2024)
- [Rasa: Building Expressive Speech Synthesis Systems for Indian Languages in Low-resource Settings](https://mlsanity.com/paper/2407.14056/) (2024)
- [Dual Script E2E framework for Multilingual and Code-Switching ASR](https://mlsanity.com/paper/2106.01400/) (2021)
- [Rapid Speaker Adaptation in Low Resource Text to Speech Systems using Synthetic Data and Transfer learning](https://mlsanity.com/paper/2312.01107/) (2023)
- [MunTTS: A Text-to-Speech System for Mundari](https://mlsanity.com/paper/2401.15579/) (2024)
- [Everyday Speech in the Indian Subcontinent](https://mlsanity.com/paper/2410.10508/) (2024)
- [BnTTS: Few-Shot Speaker Adaptation in Low-Resource Setting](https://mlsanity.com/paper/2502.05729/) (2025)
- [Kinship in Speech: Leveraging Linguistic Relatedness for Zero-Shot TTS in Indian Languages](https://mlsanity.com/paper/2506.03884/) (2025)

## Abstract (arXiv)

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.