WaveNet: A Generative Model for Raw Audio

نویسندگان

  • Aäron van den Oord
  • Sander Dieleman
  • Heiga Zen
  • Karen Simonyan
  • Oriol Vinyals
  • Alex Graves
  • Nal Kalchbrenner
  • Andrew W. Senior
  • Koray Kavukcuoglu
چکیده

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-ofthe-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.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders

Generative models in vision have seen rapid progress due to algorithmic improvements and the availability of high-quality image datasets. In this paper, we offer contributions in both these areas to enable similar progress in audio modeling. First, we detail a powerful new WaveNet-style autoencoder model that conditions an autoregressive decoder on temporal codes learned from the raw audio wave...

متن کامل

Perceptual audio loss function for deep learning

PESQ, Perceptual Evaluation of Speech Quality [5], and POLQA, Perceptual Objective Listening Quality Assessment [1] , are standards comprising a test methodology for automated assessment of voice quality of speech as experienced by human beings. The predictions of those objective measures should come as close as possible to subjective quality scores as obtained in subjective listening tests, us...

متن کامل

Music Generation Using Neural Networks

Sequence learning is attracting more and more attention both in industry and academic world with the wide usage of RNN and LSTM neural network architecture. Early this year, Google Brain team open sourced a research project named Magenta, which tries to provide a platform for musicians, artists and programmers to create their music and art works using machine intelligence. Several months later,...

متن کامل

Hybridnet: a Hybrid Neural Architecture to Speed-up Autoregressive Models

This paper introduces HybridNet, a hybrid neural network to speed-up autoregressive models for raw audio waveform generation. As an example, we propose a hybrid model that combines an autoregressive network named WaveNet and a conventional LSTM model to address speech synthesis. Instead of generating one sample per time-step, the proposed HybridNet generates multiple samples per time-step by ex...

متن کامل

Text-to-speech Synthesis System based on Wavenet

In this project, we focus on building a novel parametric TTS system. Our model is based on WaveNet(Oord et al, 2016), a deep neural network introduced by DeepMind in late 2016 for generating raw audio waveforms. It is fully probabilistic, with the predictive distribution for each audio sample conditioned on all previous samples. The model introduces the idea of convolutional layer into TTS task...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2016