Deep learning based text-to-speech (TTS) systems have been evolving rapidly
with advances in model architectures, training methodologies, and
generalization across speakers and languages. However, these advances have not
been thoroughly investigated for Indian language speech synthesis. Such
investigation is computationally expensive given the number and diversity of
Indian languages, relatively lower resource availability, and the diverse set
of advances in neural TTS that remain untested. In this paper, we evaluate the
choice of acoustic models, vocoders, supplementary loss functions, training
schedules, and speaker and language diversity for Dravidian and Indo-Aryan
languages. Based on this, we identify monolingual models with FastPitch and
HiFi-GAN V1, trained jointly on male and female speakers to perform the best.
With this setup, we train and evaluate TTS models for 13 languages and find our
models to significantly improve upon existing models in all languages as
measured by mean opinion scores. We open-source all models on the Bhashini
platform.

本研究评估了科威特琴主义和印度Ａryan 语言的声学模型、语音合成器、辅助损失函数、训练计划和说话者和语言多样性。基于此，我们确定了单语模型与 FastPitch 和 HiFi-GAN V1，联合训练男性和女性说话者表现最佳。在这个设置下，我们为 13 种语言训练和评估 TTS 模型，并发现我们的模型在所有语言中都明显优于现有模型。我们通过 Bhashini 平台开源所有模型。