Stories
Slash Boxes
Comments

SoylentNews is people

posted by janrinok on Monday September 12 2016, @05:14AM   Printer-friendly
from the what-did-you-say? dept.

Researchers at Google DeepMind have released a paper (PDF) and writeup on their new "WaveNet" neural network. WaveNet is able to generate speech that arguably sounds far better than current text-to-speech (TTS) programs, and was also used to synthesize other audio, such as piano music.

We trained WaveNet using some of Google's TTS datasets so we could evaluate its performance. The following figure shows the quality of WaveNets on a scale from 1 to 5, compared with Google's current best TTS systems (parametric and concatenative), and with human speech using Mean Opinion Scores (MOS). MOS are a standard measure for subjective sound quality tests, and were obtained in blind tests with human subjects (from over 500 ratings on 100 test sentences). As we can see, WaveNets reduce the gap between the state of the art and human-level performance by over 50% for both US English and Mandarin Chinese.

For both Chinese and English, Google's current TTS systems are considered among the best worldwide, so improving on both with a single model is a major achievement.

There are multiple audio samples included on the writeup page.

Google-owned DeepMind has presented a neural network that can generate more convincing human speech, and other forms of audio such as classical music:

To bolster their claim, DeepMind released some samples, comparing their WaveNets with samples made by concatenate and parametric TTS. You be the judge.

Parametric: parametric-1.wav [and] parametric-2.wav

And now, this is what WaveNet generated: wavenet-1.wav [and] wavenet-2.wav

Daniel (UK) will live forever.


Original Submission #1   Original Submission #2

 
This discussion has been archived. No new comments can be posted.
Display Options Threshold/Breakthrough Mark All as Read Mark All as Unread
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.