arXiv (Cornell University)· 2016· Preprint
WaveNet: A Generative Model for Raw Audio
- 3,622citations
- 2016year
Short summary
WaveNet, a deep neural network, generates raw audio waveforms by predicting each sample based on all previous ones, achieving state-of-the-art naturalness in text-to-speech synthesis.
AI-generated from the title and abstract; the full text is not read.
Key points
- WaveNet is a fully probabilistic, autoregressive deep neural network for raw audio generation.
- Achieves state-of-the-art naturalness in text-to-speech for English and Mandarin.
- Can model multiple speakers with a single network by conditioning on speaker identity.
- Shows promise in generating realistic musical fragments and for phoneme recognition.
AI-generated from the title and abstract; the full text is not read.
Abstract
This paper introduces WaveNet, a deep neural network for generating raw audio waveforms. The model is fully probabilistic and autoregressive, with the predictive distribution for each audio sample conditioned on all previous ones; nonetheless we show that it can be efficiently trained on data with tens of thousands of samples per second of audio. When applied to text-to-speech, it yields state-of-the-art performance, with human listeners rating it as significantly more natural sounding than the best parametric and concatenative systems for both English and Mandarin. A single WaveNet can capture the characteristics of many different speakers with equal fidelity, and can switch between them by conditioning on the speaker identity. When trained to model music, we find that it generates novel and often highly realistic musical fragments. We also show that it can be employed as a discriminative model, returning promising results for phoneme recognition.
The authors' abstract, as published at the source. arXiv (Cornell University), 2016 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Signal Processing
Signal ProcessingComputer Science