Semantic Scholar Open Access 2017 3007 sitasi

Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions

Jonathan Shen Ruoming Pang Ron J. Weiss M. Schuster N. Jaitly +8 lainnya

Lihat Sumber DOI

Abstrak

This paper describes Tacotron 2, a neural network architecture for speech synthesis directly from text. The system is composed of a recurrent sequence-to-sequence feature prediction network that maps character embeddings to mel-scale spectrograms, followed by a modified WaveNet model acting as a vocoder to synthesize time-domain waveforms from those spectrograms. Our model achieves a mean opinion score (MOS) of 4.53 comparable to a MOS of 4.58 for professionally recorded speech. To validate our design choices, we present ablation studies of key components of our system and evaluate the impact of using mel spectrograms as the conditioning input to WaveNet instead of linguistic, duration, and $F_{0}$ features. We further show that using this compact acoustic intermediate representation allows for a significant reduction in the size of the WaveNet architecture.

Topik & Kata Kunci

Computer Science

Penulis (13)

Jonathan Shen

Ruoming Pang

Ron J. Weiss

M. Schuster

N. Jaitly

Zongheng Yang

Z. Chen

Yu Zhang

Yuxuan Wang

R. Skerry-Ryan

R. Saurous

Yannis Agiomyrgiannakis

Yonghui Wu

Format Sitasi

APA MLA BibTeX

Shen, J., Pang, R., Weiss, R.J., Schuster, M., Jaitly, N., Yang, Z. et al. (2017). Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions. https://doi.org/10.1109/ICASSP.2018.8461368

Akses Cepat

Lihat di Sumber doi.org/10.1109/ICASSP.2018.8461368

Informasi Jurnal

Tahun Terbit: 2017
Bahasa: en
Total Sitasi: 3007×
Sumber Database: Semantic Scholar
DOI: 10.1109/ICASSP.2018.8461368
Akses: Open Access ✓