# A comparison of recent waveform generation and acoustic modeling methods for neural-network-based speech synthesis

arXiv: https://arxiv.org/abs/1804.02549 · HTML: https://mlsanity.com/paper/1804.02549/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2018.

## Built on by (most cited first, 3 of 3)

- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [Universal Neural Vocoding with Parallel WaveNet](https://mlsanity.com/paper/2102.01106/) (2021)
- [VisualTTS: TTS with Accurate Lip-Speech Synchronization for Automatic Voice Over](https://mlsanity.com/paper/2110.03342/) (2021)

## Abstract (arXiv)

Recent advances in speech synthesis suggest that limitations such as the lossy nature of the amplitude spectrum with minimum phase approximation and the over-smoothing effect in acoustic modeling can be overcome by using advanced machine learning approaches. In this paper, we build a framework in which we can fairly compare new vocoding and acoustic modeling techniques with conventional approaches by means of a large scale crowdsourced evaluation. Results on acoustic models showed that generative adversarial networks and an autoregressive (AR) model performed better than a normal recurrent network and the AR model performed best. Evaluation on vocoders by using the same AR acoustic model demonstrated that a Wavenet vocoder outperformed classical source-filter-based vocoders. Particularly, generated speech waveforms from the combination of AR acoustic model and Wavenet vocoder achieved a similar score of speech quality to vocoded speech.