MFCCGAN: A Novel MFCC-Based Speech Synthesizer Using Adversarial Learning

Mohammad Reza Hasanabadi Majid Behdad Davood Gharavian
6/22/2023
cs.SDcs.AIeess.AS

No official code found. Best implementation: MohammdReza2020/mfccgan (5 stars, last commit 2023-09-17).

Abstract

In this paper, we introduce MFCCGAN as a novel speech synthesizer based on adversarial learning that adopts MFCCs as input and generates raw speech waveforms. Benefiting the GAN model capabilities, it produces speech with higher intelligibility than a rule-based MFCC-based speech synthesizer WORLD. We evaluated the model based on a popular intrusive objective speech intelligibility measure (STOI) and quality (NISQA score). Experimental results show that our proposed system outperforms Librosa MFCC- inversion (by an increase of about 26% up to 53% in STOI and 16% up to 78% in NISQA score) and a rise of about 10% in intelligibility and about 4% in naturalness in comparison with conventional rule-based vocoder WORLD that used in the CycleGAN-VC family. However, WORLD needs additional data like F0. Finally, using perceptual loss in discriminators based on STOI could improve the quality more. WebMUSHRA-based subjective tests also show the quality of the proposed approach.

View on arXivView PDF

Code Implementations(1)

MohammdReza2020/mfccganCommunity100%

mfccgan is A Novel MFCC-Based Speech Synthesizer Using Adversarial Learning

50Jupyter NotebookMar 4, 20233 years ago

Similar Papers

Evaluating Speech Synthesis by Training Recognizers on Synthetic Speech

85% match2023

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

85% match1 repo2.4k2020

High Fidelity Speech Synthesis with Adversarial Networks

82% match1 repo1302019

LoRP-TTS: Low-Rank Personalized Text-To-Speech

82% match2025

Fast, High-Quality and Parameter-Efficient Articulatory Synthesis using Differentiable DSP

82% match2024

MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis

82% match1 repo1.0k2019

Cite this paper

@article{gharavian2023mfccgan,
  title  = {MFCCGAN: A Novel MFCC-Based Speech Synthesizer Using Adversarial Learning},
  author = {Mohammad Reza Hasanabadi Majid Behdad Davood Gharavian},
  year   = {2023},
  eprint = {2306.12785},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.12785v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2306.12785.svg)](https://codeofpaper.com/paper/2306.12785)

Discussion