# Towards Robust Neural Vocoding for Speech Generation: A Survey

arXiv: https://arxiv.org/abs/1912.02461 · HTML: https://mlsanity.com/paper/1912.02461/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Dec 2019.

## Built on by (most cited first, 8 of 8)

- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forward](https://mlsanity.com/paper/2103.00484/) (2021)
- [Adversarial Sample Detection for Speaker Verification by Neural Vocoders](https://mlsanity.com/paper/2107.00309/) (2021)
- [A Text-to-Speech Pipeline, Evaluation Methodology, and Initial Fine-Tuning Results for Child Speech Synthesis](https://mlsanity.com/paper/2203.11562/) (2022)
- [AdaVocoder: Adaptive Vocoder for Custom Voice](https://mlsanity.com/paper/2203.09825/) (2022)
- [Low-Resource End-to-end Sanskrit TTS using Tacotron2, WaveGlow and Transfer Learning](https://mlsanity.com/paper/2212.03558/) (2022)
- [Sprachsynthese -- State-of-the-Art in englischer und deutscher Sprache](https://mlsanity.com/paper/2106.06230/) (2021)
- [Creation and Detection of German Voice Deepfakes](https://mlsanity.com/paper/2108.01469/) (2021)

## Abstract (arXiv)

Recently, neural vocoders have been widely used in speech synthesis tasks, including text-to-speech and voice conversion. However, when encountering data distribution mismatch between training and inference, neural vocoders trained on real data often degrade in voice quality for unseen scenarios. In this paper, we train four common neural vocoders, including WaveNet, WaveRNN, FFTNet, Parallel WaveGAN alternately on five different datasets. To study the robustness of neural vocoders, we evaluate the models using acoustic features from seen/unseen speakers, seen/unseen languages, a text-to-speech model, and a voice conversion model. We found out that the speaker variety is much more important for achieving a universal vocoder than the language. Through our experiments, we show that WaveNet and WaveRNN are more suitable for text-to-speech models, while Parallel WaveGAN is more suitable for voice conversion applications. Great amount of subjective MOS results in naturalness for all vocoders are presented for future studies.