Artificial intelligence is not only used to create funny or weird pictures than a few words. These techniques are also very useful in modifying and improving all kinds of documents. Pixelmator, for example, uses Apple’s CoreML to enlarge images without losing much quality.
Adobe decided to take care of the audio with the tool Speech improvement Developed as part of the Shasta Project, it has simply been renamed Adobe Podcast. The principle is simple: the service takes a poor audio file, with noise and echo, which it turns into a file that can be used in a podcast. Small example:
Not too bad, even if there is a somewhat mechanical aspect to the score (the core file, it has to be said, isn’t great). However, this tool can be very useful for anyone who wants to get started with podcasting without necessarily having the software (or know-how, no harm in learning) to clean up recordings.
It’s free to use, but you still need to create an Adobe account (it’s free). Enhance Speech supports MP3 or WAV files up to 1 hour (or 1 GB). It is possible to download the result. Most hackers can go for the open source solution available on Mayavoz github.
“Hardcore beer fanatic. Falls down a lot. Professional coffee fan. Music ninja.”
More Stories
When the sun rises Radio-Canada.ca
Parhelia – auditory canal
Ocean looks from the heart in a film discussion