Details

Autor(en) / Beteiligte

• Wang, Xin
• Lorenzo-Trueba, Jaime
• Takaki, Shinji
• Juvela, Lauri
• Yamagishi, Junichi

Titel

A Comparison of Recent Waveform Generation and Acoustic Modeling Methods for Neural-Network-Based Speech Synthesis

Ist Teil von

• 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018, p.4804-4808

Ort / Verlag

IEEE

Erscheinungsjahr

2018

Link zum Volltext

• IEEE_Xplore

Quelle

IEEE Xplore (IEEE/IET Electronic Library - IEL)

Beschreibungen/Notizen

• 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.