End to End Bangla Speech Synthesis

TL;DR

This paper presents a deep learning-based end-to-end Bangla speech synthesis system that simplifies the process by eliminating the need for preprocessing and G2P conversion, achieving high naturalness with minimal data.

Contribution

The authors introduce a novel end-to-end Bangla TTS model with only three components, trained on 20 hours of data, outperforming existing systems in naturalness without complex preprocessing.

Findings

Achieved 3.79 MOS score indicating high naturalness.

Obtained 0.77 PESQ score demonstrating good speech quality.

Outperforms all existing non-commercial Bangla TTS systems.

Abstract

Text-to-Speech (TTS) system is a system where speech is synthesized from a given text following any particular approach. Concatenative synthesis, Hidden Markov Model (HMM) based synthesis, Deep Learning (DL) based synthesis with multiple building blocks, etc. are the main approaches for implementing a TTS system. Here, we are presenting our deep learning-based end-to-end Bangla speech synthesis system. It has been implemented with minimal human annotation using only 3 major components (Encoder, Decoder, Post-processing net including waveform synthesis). It does not require any frontend preprocessor and Grapheme-to-Phoneme (G2P) converter. Our model has been trained with phonetically balanced 20 hours of single speaker speech data. It has obtained a 3.79 Mean Opinion Score (MOS) on a scale of 5.0 as subjective evaluation and a 0.77 Perceptual Evaluation of Speech Quality(PESQ) score on a scale of [-0.5, 4.5] as objective evaluation. It is outperforming all existing non-commercial state-of-the-art Bangla TTS systems based on naturalness.