MFCCGAN: A Novel MFCC-Based Speech Synthesizer Using Adversarial Learning
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 20 of its 41 references that are in the map. First posted on arXiv 22 Jun 2023.
Builds on
20 of 41 references.
References · 20
- 2017Neural Discrete Representation Learningcited by 4,712
- 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
- 2016Least Squares Generative Adversarial Networkscited by 1,001
- 2016Conditional Image Generation with PixelCNN Decoderscited by 862
- 2021SoundStream: An End-to-End Neural Audio Codeccited by 771
- 2017Generative Adversarial Networks: An Overviewcited by 590
- 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 354
- 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 309
- 2018Efficient Neural Audio Synthesiscited by 219
- 2021NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasetscited by 192
- 2019GANSynth: Adversarial Neural Audio Synthesiscited by 116
- 2020An Overview of Voice Conversion and its Challenges: From Statistical Modeling to Deep Learningcited by 112
8 more
- 2018LPCNet: Improving Neural Speech Synthesis Through Linear Predictioncited by 110
- 2019MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancementcited by 104
- 2019CycleGAN-VC2: Improved CycleGAN-based Non-parallel Voice Conversioncited by 46
- 2017Wavenet based low rate speech codingcited by 33
- 2017Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networkscited by 31
- 2016Speex: A Free Codec For Free Speechcited by 6
- 2018Speech waveform synthesis from MFCC sequences with generative adversarial networkscited by 5
- 2021High-Quality Vocoding Design with Signal Processing for Speech Synthesis and Voice Conversioncited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.