February 20, 2020

Artificial Intelligence

Artificial Intelligence
Hits: 54

The results aren’t perfect, but you can sort of hear how Google’s translator was able to retain the voice and tone of the original speaker. It can do this because it converts audio input directly to audio output without any intermediary steps. In contrast, traditional translational systems convert audio into text, translate the text, and then resynthesize the audio, losing the characteristics of the original voice along the way.The new system, dubbed the Translatotron, has three components, all of which look at the speaker’s audio spectrogram—a visual snapshot of the frequencies used when the sound is playing, often called a voiceprint.  The first component uses a neural network trained to map the audio spectrogram in the input language to the audio spectrogram in the output language. The second converts the spectrogram into an audio wave that can be played. The third component can then layer the original speaker’s vocal characteristics back into the final audio output.

Tags:
Artificial Intelligence
Hits: 94

Opioid addiction is easily one of the top widespread healthcare issues facing the U.S., and research indicates we’re nowhere near achieving any kind of significant mitigating solution. But a team of medical researchers working at the West Virginia University Rockefeller Neuroscience Institute (RNI) and West Virginia University Medicine (WVU) are beginning a new clinical trial of a solution that uses brain-embedded technology to potentially curb opioid addiction in cases that have resisted other methods of treatment.

Tags: