AI - AI Dynamics

→ View original post on X — @mit_csail

Ivan Sutherland’s Sketchpad: Pioneering CAD Technology in 1963

By

@mit_csail

–

07 January 2023 18h00

#otd in 1963 MIT PhD student Ivan Sutherland unveiled his “Sketchpad”, which pioneered the CAD technology used in today’s computers: http://
ti.me/2rj5Q2f

→ View original post on X — @berkeley_ai

John Schulman: OpenAI Cofounder Behind ChatGPT Success

By

@berkeley_ai

–

07 January 2023 17h39

There’s been a lot of buzz about #ChatGPT on Twitter lately — the main architect behind the system is none other than @berkeley_ai alumni and OpenAI cofounder @johnschulman2
! Hats off to John and the team!

→ View original post on X — @levelsio

Spending AI Budget and Investment Allocation

By

@levelsio

–

07 January 2023 17h30

That's okay, need to spend my AI money

→ View original post on X — @sallyeaves

Green IT and Energy Sustainability in AI Networking

By

@sallyeaves

–

07 January 2023 17h15

Its #Green IT #Energy & #Sustainability ! Ami Badani VP #networking @nvidia http://
bit.ly/GreenITNvidia @techradiottt With #Research @ericsson @RedHat @vmware #NVIDIA #partner @NVIDIAAI #SDGs #CES2023
#AI #100DaysOfCode #womenintech @mikeflache #5G #podcast @EstelaMandela

Technical mechanism of AI-driven voice synthesis

By

–

07 January 2023 17h07

It generates a series of codes based on the phonemes and an audio recording of the speaker's voice.

These codes are then turned directly into a waveform, which allows it to generate speech that sounds like the speaker from just a small amount of reference audio.

Example (🔊): pic.twitter.com/HQvjJUnbiH
— AI Breakfast (@AiBreakfast) 7 janvier 2023

It generates a series of codes based on the phonemes and an audio recording of the speaker's voice. These codes are then turned directly into a waveform, which allows it to generate speech that sounds like the speaker from just a small amount of reference audio. Example ():

Technical architecture of the VALL-E generative audio model

By

–

07 January 2023 17h07

Instead of turning text into a series of specific sounds (called phonemes) and then into a visual representation of the sound called a mel-spectrogram, and then into a waveform (a digital representation of sound that can be played through a speaker) VALL-E takes a shortcut:

VALL-E: A new approach to natural-sounding AI speech synthesis

By

–

07 January 2023 17h07

VALL-E is significantly better at synthesizing natural-sounding speech and accurately reproducing the characteristics of a speaker compared to anything else available. VALL-E takes a different approach than previous systems for synthesizing speech:

VALL-E: New Language Modeling Approach for Text-to-Speech

By

–

07 January 2023 17h07

Digitally clone your own voice in 3 seconds: VALL-E

Inside the new language modeling approach for text-to-speech synthesis: pic.twitter.com/slaX1P3sqz
— AI Breakfast (@AiBreakfast) 7 janvier 2023

Digitally clone your own voice in 3 seconds: VALL-E Inside the new language modeling approach for text-to-speech synthesis:

Technical overview of an AI voice synthesis training model

By

–

07 January 2023 17h07

The language model was trained on a huge amount of data (60,000 hours of English speech) and combines it with just 3 seconds of a person's voice and uses that to synthesize new, high-quality speech that sounds like the original speaker. pic.twitter.com/tIaimhfQ9R
— AI Breakfast (@AiBreakfast) 7 janvier 2023

The language model was trained on a huge amount of data (60,000 hours of English speech) and combines it with just 3 seconds of a person's voice and uses that to synthesize new, high-quality speech that sounds like the original speaker.