/
Navigation
C
Chronicles
Browse all articles
C
E
Explore
Semantic exploration
E
R
Research
Entity momentum
R
N
Nexus
Correlations & relationships
N
~
Story Arc
Topic evolution
S
Drift Map
Semantic trajectory animation
D
P
Posts
Analysis & commentary
P
Browse
@
Entities
Companies, people, products, technologies
Domains
Browse by publication source
Handles
Browse by social media handle
Detection
?
Concept Search
Semantic similarity search
!
High Impact Stories
Top coverage by position
+
Sentiment Analysis
Positive/negative coverage
*
Anomaly Detection
Unusual coverage patterns
Analysis
vs
Rivalry Report
Compare two entities head-to-head
/\
Semantic Pivots
Narrative discontinuities
!!
Crisis Response
Event recovery patterns
Connected
Nav: C E R N
Search: /
Command: ⌘K
Embeddings: large
VOICE ARCHIVE

Keunwoo Choi

@keunwoochoi
10 posts
2024-11-26
wow! i'd say this is probably the first ChatGPT moment (or Llama3 moment) in audio/music/speech. check out the video demo. congrats, @RafaelValleArt et al.!
2024-11-26 View on X
Reuters

Nvidia unveils Fugatto, an AI model for generating music and audio that can also modify voices, trained on open-source data, and weighs whether to release it

an impressive new AI sound model from Nvidia Mandy Dalugdug / Music Business Worldwide : Nvidia unveils AI audio generator ‘Fugatto’ that can produce ‘sounds never heard before’ Su...

2024-07-24
i admit i underestimated how quickly the community (largely thanks to Meta, of course) could catch up OpenAI. impressive.
2024-07-24 View on X
Bloomberg

Meta debuts Llama 3.1 405B, the “first frontier-level open source AI model”, as well as new Llama 3.1 70B and 8B models, and says it's working on Llama 4

i admit i underestimated how quickly the community (largely thanks to Meta, of course) could catch up OpenAI. impressive.
2024-07-24 View on X
Meta

Mark Zuckerberg argues that “open source AI” is the path forward, closed models are vulnerable to vendor lock-in and state-backed espionage, and more

RE: https://www.threads.net/... Dare Obasanjo / @carnage4life : You can find @zuck's full post here https://www.facebook.com/... Dare Obasanjo / @carnage4life : Mark Zuckerberg has...

2024-04-23
> The innovation lies _entirely_ in our dataset for training, .. Phi-3-mini (3.8B) beats llama3-8B 🙀
2024-04-23 View on X
The Verge

Microsoft debuts Phi-3 Mini, a small 3.8B-parameter model about as capable as GPT-3.5, and plans Phi-3 Small and Phi-3 Medium models with 7B and 14B parameters

Microsoft launched the next version of its lightweight AI model Phi-3 Mini, the first of three small models the company plans to release.

2023-11-17
THIS IS BIG! All the music folks in Google Deepmind focus on one thing: AI music generation while NOT exploiting artists. Nothing is perfect, there're probably still some holes in giving the credit, but this is better than anything ever for very sure.
2023-11-17 View on X
Wired

YouTube previews Dream Track and Music AI tools, which use DeepMind's new model Lyria to generate music in the style of famous artists, from humming, and more

Will Knight / Wired :

2023-11-16
THIS IS BIG! All the music folks in Google Deepmind focus on one thing: AI music generation while NOT exploiting artists. Nothing is perfect, there're probably still some holes in giving the credit, but this is better than anything ever for very sure.
2023-11-16 View on X
Wired

YouTube lets some Shorts creators test Dream Track, a new DeepMind-powered AI tool to generate and remix music in the styles of nine artists, including Sia

YouTube creators will get to test a new AI tool that generates and remixes music in the style of several famous musicians, including Sia, Demi Lovato, and T-Pain.

2023-01-28
whoa, this is bigger than ChatGPT to me. google almost solved music generation, i'd say. https://google-research.github.io/ ...
2023-01-28 View on X
TechCrunch

Google researchers detail AI model MusicLM, which can generate high-fidelity music in any genre from text and was trained on a dataset of 280K hours of music

An impressive new AI system from Google can generate music in any genre given a text description.  But the company, fearing the risks, has no immediate plans to release it.

really well done, from SoundStream and AudioLM through MuLan to MusicLM 👏👏 the overall structure of MusicLM = MuLan + AudioLM = MuLan + w2v-BERT + SoundStream https://twitter.com/...
2023-01-28 View on X
TechCrunch

Google researchers detail AI model MusicLM, which can generate high-fidelity music in any genre from text and was trained on a dataset of 280K hours of music

An impressive new AI system from Google can generate music in any genre given a text description.  But the company, fearing the risks, has no immediate plans to release it.

+ they released MusicCaps dataset (5521 music-text pair) which they used as an eval set. https://www.kaggle.com/....
2023-01-28 View on X
TechCrunch

Google researchers detail AI model MusicLM, which can generate high-fidelity music in any genre from text and was trained on a dataset of 280K hours of music

An impressive new AI system from Google can generate music in any genre given a text description.  But the company, fearing the risks, has no immediate plans to release it.

to recap, i find the whole roadmap really, really brilliant. - because there's MuLan, they could use audio-only dataset. - because there's SoundStream, the music generation task was simplified to token generation, not waveform generation.
2023-01-28 View on X
TechCrunch

Google researchers detail AI model MusicLM, which can generate high-fidelity music in any genre from text and was trained on a dataset of 280K hours of music

An impressive new AI system from Google can generate music in any genre given a text description.  But the company, fearing the risks, has no immediate plans to release it.