Can you tell the two apart? [Read More]
Summary… * Machine-Made
The system is Google’s second official generation of the technology, which consists of two deep neural networks.
That spectrogram is then fed into WaveNet, a system from Alphabet’s #AI research lab DeepMind, which reads the chart and generates the corresponding audio elements accordingly.
Keep in mind one sample from each sentence is generated by #AI, and the other is a human hired by Google.
(However, if you reveal the “page source” and look at the filenames of each on the Google research website, one is labeled “gen,” ostensibly to mark the generated sample.)
Updated: This story has been updated to reflect that two of the audio clips are humans speaking, not #AI-generated voices.
Opinion… * Man-Made
The second official generation of Google’s text-to-speech technology, claims near-human accuracy at imitating audio of a person speaking from text. Only last year, this was predicted by top #AI researchers for the year 2024. #Trend