Fast Griffin Lim based Waveform Generation Strategy for Text-to-Speech Synthesis

TL;DR

This paper introduces a faster speech waveform generation method for text-to-speech systems using Fast Griffin Lim Algorithm, significantly reducing synthesis delay and improving speech quality for real-time applications.

Contribution

The paper proposes replacing GLA with FGLA in TTS systems to achieve faster convergence and lower synthesis delay, enhancing real-time speech synthesis performance.

Findings

36.58% reduction in synthesis delay

Improved speech quality with higher MOS scores

Faster convergence compared to GLA

Abstract

The performance of text-to-speech (TTS) systems heavily depends on spectrogram to waveform generation, also known as the speech reconstruction phase. The time required for the same is known as synthesis delay. In this paper, an approach to reduce speech synthesis delay has been proposed. It aims to enhance the TTS systems for real-time applications such as digital assistants, mobile phones, embedded devices, etc. The proposed approach applies Fast Griffin Lim Algorithm (FGLA) instead Griffin Lim algorithm (GLA) as vocoder in the speech synthesis phase. GLA and FGLA are both iterative, but the convergence rate of FGLA is faster than GLA. The proposed approach is tested on LJSpeech, Blizzard and Tatoeba datasets and the results for FGLA are compared against GLA and neural Generative Adversarial Network (GAN) based vocoder. The performance is evaluated based on synthesis delay and speech quality. A 36.58% reduction in speech synthesis delay has been observed. The quality of the output speech has improved, which is advocated by higher Mean opinion scores (MOS) and faster convergence with FGLA as opposed to GLA.