# Probability density distillation with generative adversarial networks for high-quality parallel waveform generation

arXiv: https://arxiv.org/abs/1904.04472 · HTML: https://mlsanity.com/paper/1904.04472/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2019.

## Built on by (most cited first, 14 of 14)

- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [CaloFlow II: Even Faster and Still Accurate Generation of Calorimeter Showers with Normalizing Flows](https://mlsanity.com/paper/2110.11377/) (2021)
- [Audio representations for deep learning in sound synthesis: A review](https://mlsanity.com/paper/2201.02490/) (2022)
- [NeRAF: 3D Scene Infused Neural Radiance and Acoustic Fields](https://mlsanity.com/paper/2405.18213/) (2024)
- [Collaborative Watermarking for Adversarial Speech Synthesis](https://mlsanity.com/paper/2309.15224/) (2023)
- [A Systematic Comparison of Phonetic Aware Techniques for Speech Enhancement](https://mlsanity.com/paper/2206.11000/) (2022)
- [A Survey of Deep Learning Audio Generation Methods](https://mlsanity.com/paper/2406.00146/) (2024)
- [Distilling the Knowledge from Conditional Normalizing Flows](https://mlsanity.com/paper/2106.12699/) (2021)
- [Unified Source-Filter GAN: Unified Source-filter Network Based On Factorization of Quasi-Periodic Parallel WaveGAN](https://mlsanity.com/paper/2104.04668/) (2021)
- [Multi-Loss Convolutional Network with Time-Frequency Attention for Speech Enhancement](https://mlsanity.com/paper/2306.08956/) (2023)
- [Building a Luganda Text-to-Speech Model From Crowdsourced Data](https://mlsanity.com/paper/2405.10211/) (2024)
- [AudioVisual Speech Synthesis: A brief literature review](https://mlsanity.com/paper/2103.03927/) (2021)
- [FlowVocoder: A small Footprint Neural Vocoder based Normalizing flow for Speech Synthesis](https://mlsanity.com/paper/2109.13675/) (2021)
- [Evaluating Neural Networks Architectures for Spring Reverb Modelling](https://mlsanity.com/paper/2409.04953/) (2024)

## Abstract (arXiv)

This paper proposes an effective probability density distillation (PDD) algorithm for WaveNet-based parallel waveform generation (PWG) systems. Recently proposed teacher-student frameworks in the PWG system have successfully achieved a real-time generation of speech signals. However, the difficulties optimizing the PDD criteria without auxiliary losses result in quality degradation of synthesized speech. To generate more natural speech signals within the teacher-student framework, we propose a novel optimization criterion based on generative adversarial networks (GANs). In the proposed method, the inverse autoregressive flow-based student model is incorporated as a generator in the GAN framework, and jointly optimized by the PDD mechanism with the proposed adversarial learning method. As this process encourages the student to model the distribution of realistic speech waveform, the perceptual quality of the synthesized speech becomes much more natural. Our experimental results verify that the PWG systems with the proposed method outperform both those using conventional approaches, and also autoregressive generation systems with a well-trained teacher WaveNet.