#VoCo. Adobe Audio Manipulator Sneak Peak with Jordan Peele | Adobe Creative Cloud
Channel:Adobe Creative Cloud · Length:7:20 · Published:2016-11-04 · Views:1850552
Summary
Adobe's VoCo demo from the MAX 2016 Sneak Peeks, co-hosted by Jordan Peele, showing software that changes words in a voiceover by typing new ones.
Why HN recommends it
HN cites it as the early example of voice cloning and audio deepfakes, with some recommending Peele's reaction and others calling the demo fake or never shipped.
I really recommend the Adobe demonstration of their VoCo speech audio "photoshopping" because of Jordan Peele's reaction — HN, 2017
LLMs & generative AI · Computer vision, speech & NLP · Music theory, synthesis & production
Subtitles (excerpt)
let's hear from zuu about Photoshop voiceovers please welcome to the stage zuu Z hello everyone you guys have been making weird stuff online with photo editing well we'll do the next thing today let's do something to human speech like changing what you have said in your wedding so let's get on to it well I have obtained this piece of audio where um there's me key talking to PE about his feeling after getting nominated uh there's a pretty interesting uh joke here so let's uh let's just hear it but she's a oh no out of here uh I jumped on the bed and um and uh I kissed my dogs and my wife in that order yeah so how about we uh mess with uh who he actually kissed well you may have you may be thinking okay we're pretty familiar with photoshops but we are not quite used to audio waveforms uh how can we do this well I have a good news for you introducing project project vocal project vocal allows you to edit speech in text so let's bring it up um so I just load this audio piece into a vocal so wait a second and uh we have this so as you can see let me zoom in a little bit um so as you can see we have the audio waveform above it and we have the text under it and when we play back the text and
On Hacker News
The "Adobe Photoshop for voice" is quite amazing: [VIDEO] (you can skip the first ~third to get to the demo) — BrandoElFollito, 2018-01
I really recommend the Adobe demonstration of their VoCo speech audio "photoshopping" because of Jordan Peele's reaction: [VIDEO] . More technology demos should have unscripted, sincere reactions like that. — kmfrk, 2017-07
I really recommend the Adobe demonstration of their VoCo speech audio "photoshopping" because of Jordan Peele's reaction: [VIDEO] . More technology demo should have unscripted, sincere reactions like that. — kmfrk, 2017-07
I remember when Adobe demoed this idea of being able to edit waveforms by the recognized text back in 2016 and it was pretty mind blowing for the time. [VIDEO] EDIT: I could also definitely see Audapolis being useful if you could integrate it into a podcast's post processing flow (volume normalization, de-essing) by recognizing certain verbal tics and automatically removing them from the audio su… — vunderba, 2024-07
There was Adobe Voco, which seemed kind of a forerunner: [VIDEO] , [LINK] . It purportedly could edit speech like an audio editor and looked like a destroyer of authenticity. And then nothing was heard of it anymore. (Edit: Wikipedia says that VoCo takes “approximately 20 minutes of the desired target's speech”, and that it was a research prototype.) There was a thing called Tacotron from a team … — aasasd, 2021-12
Related videos
- A Brief History of Quantum Mechanics - with Sean Carroll · The Royal Institution · 56:11
- Axis of Awesome - 4 Four Chord Song (with song titles) · random804 · 5:31
- Music Theory and White Supremacy · Adam Neely · 44:01
- Transformers, the tech behind LLMs | Deep Learning Chapter 5 · 3Blue1Brown · 27:14
- Deep Dive into LLMs like ChatGPT · Andrej Karpathy · 3:31:23
- Music Software & Bad Interface Design: Avid’s Sibelius · Tantacrul · 21:35
- Let's build GPT: from scratch, in code, spelled out. · Andrej Karpathy · 1:56:20
- Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learning · Google TechTalks · 48:10
- A Hackers' Guide to Language Models · Jeremy Howard · 1:31:13
- Trackers: The Sound of 16-Bit · Ahoy · 41:11
- Functional Composition - Chris Ford · ClojureTV · 39:21
- Intro to Synthesis Part 1 - The Building Blocks of Sound & Synthesis · matrixsynth · 56:11
- "Voice Driven Development: Who needs a keyboard anyway?" by Emily Shea · Strange Loop Conference · 41:17
- Andrej Karpathy - AI for Full-Self Driving at Tesla · Matroid · 30:08
- [1hr Talk] Intro to Large Language Models · Andrej Karpathy · 59:48
- The Marvel Symphonic Universe · Every Frame a Painting · 13:35