Wavenet: A Generative Model For Raw Audio

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyoord2016wavenet

Related papers

• Flowavenet : A Generative Flow For Raw Audio (2018)0.00
• Parallel Wavenet: Fast High-fidelity Speech Synthesis (2017)0.00
• Melnet: A Generative Model For Audio In The Frequency Domain (2019)0.00
• Wasserstein GAN And Waveform Loss-based Acoustic Model Training For Multi-speaker Text-to-speech Synthesis Systems Using A Wavenet Vocoder (2018)12.61
• Diffwave: A Versatile Diffusion Model For Audio Synthesis (2020)0.00
• A Comparison Of Recent Waveform Generation And Acoustic Modeling Methods For Neural-network-based Speech Synthesis (2018)11.76
• Speaker-independent Raw Waveform Model For Glottal Excitation (2018)9.76
• Lp-wavenet: Linear Prediction-based Wavenet Speech Synthesis (2018)0.00