Luke Miner (@Luke_Miner) profile picture

Luke Miner

@Luke_Miner

Data scientist to the stars. Recovering economist.

 San Francisco, CA
Joined June 2010
  • Tweets119
  • Following111
  • Followers86
I wrote a piece and the New York Times is on it! nytimes.com/2019/05/22/opini…
Opinion | For a Longer, Healthier Life, Share Your Data (Published 2019)

Opinion | For a Longer, Healthier Life, Share Your Data (Published 2019)

Privacy protections are standing in the way of artificial-intelligence programs that could diagnose cancers and screen for genetic disorders.

nytimes.com
1
1
10
Luke Miner retweeted
jessica powell (@themoko) profile picture
jessica powell
@themokoOct 21
What do a Lite-Brite and AI have in common? Here’s source separation, explained with a children’s toy from 1967. 👇

Source Separation Explained with a Lite Brite

Source separation splits a mixed recording into its individual sounds. AudioShake CEO Jessica Powell explains how it works, and the difference between traditional source separation and genAI.

3
4
2
13
1,328
Luke Miner retweeted
jessica powell (@themoko) profile picture
jessica powell
@themokoOct 1
NVIDIA's new diarizer just hit #1 on the @voicearena_ai leaderboard. So naturally, we put it in a crowded room. On 8-speaker LibriCSS, @AudioShakeAI Multi-Speaker had 52% fewer word errors than Nemotron 3 (15.4% vs. 31.9%). Put us in, coach!
Image from jessica powell (@themoko)
1
1
1
2
760
Luke Miner retweeted
jessica powell (@themoko) profile picture
jessica powell
@themokoSep 1
Today we're releasing @AudioShakeAI Multi-Speaker 2.0: one recording of several people talking goes in, a clean labeled track per person comes out — including the moments they talk over each other.
2
2
8
510
Luke Miner retweeted
AudioShake (@AudioShakeAI) profile picture
AudioShake@AudioShakeAIApr 21
"I'm going to Disney World" is almost synonymous with winning the @SuperBowl. @ESPN wanted the original Phil Simms clip for their 2026 ad — but the music was baked in. We pulled his voice from the mix. Watch: youtube.com/watch?v=w1l3z-tm…
Image from AudioShake (@AudioShakeAI)
1
2
7
189
Luke Miner retweeted
AudioShake (@AudioShakeAI) profile picture
AudioShake@AudioShakeAIApr 14
Launching today: Dialogue RT, AudioShake's real-time dialogue isolation model. 11ms end-to-end latency. The first AI dialogue isolation model built for live broadcast, sports audio, and captioning pipelines that can't wait for post-production. SDK available now.
2
3
8
326
Our Series A was just the headline — this is the story. The @AudioShakeAI team is what makes it all possible: researchers, engineers & creatives working to make the world’s sound more usable for humans and machines. We’re just getting started. → audioshake.ai/post/series-a-…
Image from AudioShake (@AudioShakeAI)
Image from AudioShake (@AudioShakeAI)
1
4
127
What is AudioShake? Why did we raise $14M? And what happens next? 👀Who better to tell you than CEO @themoko
2
6
196
🎵 Big news: AudioShake raises $14M Series A to make the world’s audio editable, searchable, and programmable.
Image from AudioShake (@AudioShakeAI)
2
4
3
18
4,490
New paper from our Research team ahead of #ISMIR2024 (@cifkao @h_schreiber @faroit @Luke_Miner) evaluates our new lyrics transcription benchmark (🧵) on several transcription systems.
Ondřej Cífka (@cifkao) profile pictureOndřej Cífka@cifkao14 Aug 2024
"Lyrics Transcription for Humans", accepted to #ISMIR2024, is now online: arxiv.org/abs/2408.06370 We evaluated more models (Whisper v3, OWSM v3.1, @AudioShake v3) on our benchmark and included plots detailing what kinds of errors different models make on lyrics transcription. 🧵
Image from Ondřej Cífka (@cifkao)
1
1
6
524
In Deer Valley, @audioshakeai CEO @themoko spoke to @KPMG_US #KPMGTechandInnovation24 #Innovation audience on the #futureofaudio and what is possible when we can separate and access the different components of #sound.
Image from AudioShake (@AudioShakeAI)
1
3
169
See you at @ISMIRConf 2024! @AudioShakeAI 's Research team will present its research on lyrics transcription in San Francisco in November.
Ondřej Cífka (@cifkao) profile pictureOndřej Cífka@cifkao1 Jul 2024
Looking forward to presenting our lyrics transcription benchmark at #ISMIR2024 in San Francisco! Our paper grew from last year's LBD to a full paper with more results, which has now been accepted, so stay tuned! audioshake.github.io/jam-alt…

Jam-ALT: A Readability-Aware Lyrics Transcription Benchmark

audioshake.github.io
2
18
801
One for me and everyone else thinking they were singing about Mike Pence setting fire to the stage
AudioShake (@AudioShakeAI) profile pictureAudioShake@AudioShakeAI4 Jun 2024
We can't stop listening, we were also making up the words until now. Here's a little lyric video for those who need it.
1
5
571
Replying to @Channel4News
It was a little hard to hear – so we fixed it for you @Channel4News!
2
4
3
10
1,738
After an unreleased performance of the Tomasz Stanko Quintet was found, @AstigmaticRec turned to AudioShake to create stems of the 50-year-old recording. More on our work helping to master this radio broadcast turned vinyl album, “Wooden Music II”: audioshake.ai/post/astigmati…
Image from AudioShake (@AudioShakeAI)
3
4
352
Our paper on lyrics transcription evaluation is on arXiv with updated and extended results (including Whisper v3)! 📄 arxiv.org/abs/2311.13987 Also, the benchmark is now on @paperswithcode: 🏆 paperswithcode.com/dataset/j… 👏 @faroit @h_schreiber @Luke_Miner @cnst_ant @AudioShakeAI
Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark

Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark

Current automatic lyrics transcription (ALT) benchmarks focus exclusively on word content and ignore the finer nuances of written lyrics including formatting and punctuation, which leads to a...

arxiv.org
AudioShake (@AudioShakeAI) profile pictureAudioShake@AudioShakeAI29 Nov 2023
This month at #ISMIR2023, AudioShake’s Research team presented a new benchmark for automatic lyric transcription systems– one that accounts for the nuances of music. You can read more on their new paper on AudioShake: audioshake.ai/post/new-bench…
Image from AudioShake (@AudioShakeAI)
1
2
15
1,287
AudioShake stems power AI lyric transcription! With our industry-leading vocal stem separation, we can now transcribe and align lyrics in seconds, utilizing nothing more than the original recording as an input. Read more: medium.com/audioshake/introd…
Introducing LyricSync for Lyric Transcription & Alignment

Introducing LyricSync for Lyric Transcription & Alignment

LyricSync creates clean, time-stamped lyric transcriptions with high accuracy — using AudioShake’s award-winning vocal isolation…

medium.com
4
17
1,833
lol who did this
Image from John B. Holbein (@JohnHolbein1)
114
1,772
303
21,948
New artist profile @BillyBadnewz ! #musicproduction #MusicProducer
1
2
4
Since we know what's "inside" a piece of music, we thought it'd be fun to create a music video directed by…the music! We fed the song and album cover for the classic "Undone" by @weezer, to our AI, letting the guitar and other audio elements decide what happens to the images
1
2
10
help launch meta-science @JPAL w/ me and the incomparable Heidi Williams povertyactionlab.org/careers…
1
29
8
89
Load more