Adobe is developing Photoshop for Audio Files that will let you add words one never said.
Adobe’s developer Zeyu Jin revealed while speaking at the Adobe Max conference in San Diego, California, that the company will soon be introducing a unique software that would serve as a Photoshop for audio files. This project has been dubbed as Project VoCo. However, Jin couldn’t tell exact time frame of the launching of this new software. The software is unique because it can add words which originally aren’t part of the audio file.
Also Read: Futuristic Smart-Glove Can Translate Sign Language Into Text and Speech
This project is in its initial phases of development and it is a collaborative effort between Adobe Research and Princeton University. Project VoCo will be equipped with state-of-the-art editing facilities and will be having speech editing and noise-cancellation features as well, which is not found in any other audio file editing software. It can also generate new words in the speaker’s own voice by replicating the recorded voice. This means, the software has the capability of understanding anyone’s voice style and then imitate it. It is, however, a requirement that the recorded speech is at least 20 minutes long.
While explaining the idea behind Project VoCo, Jin demonstrated by letting the program to add a new word to a sentence by replicating the speaker’s voice.
An official Adobe statement:
“When recording voiceovers, dialog, and narration, people would often like to change or insert a word or a few words due to either a mistake they made or simply because they would like to change part of the narrative. We have developed a technology called Project VoCo in which you can simply type in the word or words that you would like to change or insert into the voiceover. The algorithm does the rest and makes it sound like the original speaker said those words.”
This is an amazing new tool that can give birth to a whole new world of possibilities as it would provide so many variations in the way we manage sound and edit them. It can also help audio engineers while they manipulate sound, improve audio clips and clean up podcasts and recordings.
Also Read: Artificial Intelligence can Decode and Unblur Pixelated Images
We must not forget the ethical implications associated with the creation of this type of program since the software can add completely new sentences to any speech, which might not fully be in that person’s interest. Doctoring audio files are not something that would go down well with the public. But as we have learned to cope with Photo-shopped images then probably one day we would learn to tolerate programs like project VoCo and let the engineers play with voices.