The team still has work to do w/the current iteration of their model: it struggles w/some consonants, like "z," which led to inaccurate impressions of sounds like bees buzzing. They also can’t yet replicate how humans imitate speech, music, or sounds that are imitated
GENERATIVE AI
-
New AI Model Generates Realistic Sounds from Text Descriptions
By
–
Authors: Matt Caren, Kartik Chandra (
@_k_a_c_h_
), Joshua B. Tenenbaum, Jonathan Ragan-Kelley (
@jrk
), & Karima Ma
Paper: https://
bit.ly/3ViqFKK
Full video: https://
bit.ly/4ikE7YG Listen to more sounds from their model: https://
bit.ly/3OzS6fn -
AI Model Learns Human Vocal Imitation Through Iterative Development
By
–
The team developed three increasingly nuanced versions of the model to compare to human vocal imitations. First, they created a baseline model that simply aimed to generate imitations that were as similar to real-world sounds as possible — but this model didn’t match human
-
Communicative Models: How AI Understands Distinctive Sound Features
By
–
Their second "communicative" model considers what’s distinctive about a sound to a listener. For instance, you’d likely imitate the sound of a motorboat by mimicking the rumble of its engine, since that’s its most distinctive auditory feature. As a final layer of reasoning, they
-
AI Model Generates Realistic World Sounds and Audio Imitations
By
–
The model can effectively take many sounds from the world & generate human-like imitations of them — including noises like leaves rustling, a snake’s hiss, & an approaching ambulance siren. pic.twitter.com/q2sOB0Tl9d
— MIT CSAIL (@MIT_CSAIL) 5 décembre 2024The model can effectively take many sounds from the world & generate human-like imitations of them — including noises like leaves rustling, a snake’s hiss, & an approaching ambulance siren.
-
AI Model Converts Vocal Imitations to Real-World Sounds
By
–
Their model can also be run in reverse to guess real-world sounds from human vocal imitations, similar to how some computer vision systems can retrieve high-quality images based on sketches.
-
AI Model Enables Intuitive Sound Design and Language Learning Applications
By
–
This model could potentially lead to more intuitive "imitation-based" interfaces for sound designers, more human-like AI characters in virtual reality, & even methods to help students learn new languages.
-
AIBI: AI-Powered Interview Platform Transforms Hiring Process
By
–
Meet AIBI: The Future of Interviews, powered by Cerebras Inference ⚡️
— Cerebras (@cerebras) 5 décembre 2024
Get instant insights, feedback and real-time follow up questions. Read how the hiring process is about to change: https://t.co/lKdvJ1HAIN pic.twitter.com/mQKYoAsTq6Meet AIBI: The Future of Interviews, powered by Cerebras Inference Get instant insights, feedback and real-time follow up questions. Read how the hiring process is about to change: https://
bit.ly/4il642w -
O1 targets early adopters: PhDs, scientists, and engineers first
By
–
Not at all surprised that the o1 demos were extremely advanced and technical (and not business-oriented). They're catering toward first adopters. And those first adopters will be PhDs, scientists, and engineers.
-
Perplexity expands Publishers Program with 15 new partners
By
–
Today, we’re excited to welcome 15 new partners to Perplexity’s Publishers’ Program. Collectively, they span more than 25 countries and 75 US communities, reporting on topics of local importance and subjects like marketing, history, and popular culture. Their contributions to