Andrew Rosenberg

Speech Researcher

[Ankur Bapna @ankurbpn]

Finally, native audio generation with Gemini! https://t.co/R8XelMjD7l

[Haohe Liu @LiuHaohe]

It's nice to see SemantiCodec taking the lead in audio codec semantic information benchmarking, even at a much lower bitrate. Paper result cross-validated!

Great work! @realHaibinWu et al.

[Shinji Watanabe @shinjiw_at_cmu]

I'm attaching the slides of my survey talk at Interspeech '24. I received many requests to share it. https://t.co/I2OD2W1t5Z

We're now in a very exciting stage of unifying all our tasks. Let's work together!

[Heiga Zen (全 炳河) @heiga_zen]

LibriTTS has been ranked 6th. Congrats to all authors and collaborators! And thanks to all users.

[Andrew Rosenberg @andrewmaxr]

Hi friends, I'll be giving a talk at this tomorrow. If you're in Kos for #INTERSPEECH2024 come by! (Also, now you know the location.)

[Ahmed Ali @ahmedalitweet1]

Explore the potential of synthetic data for ASR, TTS, and foundational speech models at the first Syndata4GenAI workshop. Join us on August 31 at 8 AM in the Ialyssos Room at the Kipriotis Panorama Hotel, KOS, Greece, co-located with #INTERSPEECH2024 https://t.co/XKSDNmIAsV

[Ahmed Ali @ahmedalitweet1]

Explore the potential of synthetic data for ASR, TTS, and foundational speech models at the first Syndata4GenAI workshop. Join us on August 31 at 8 AM in the Ialyssos Room at the Kipriotis Panorama Hotel, KOS, Greece, co-located with #INTERSPEECH2024 https://t.co/XKSDNmIAsV

[Shinji Watanabe @shinjiw_at_cmu]

Our workshop is getting close!

We have a fantastic group of keynote speakers and posters waiting for you on August 31st, on the island of Kos, Greece, right before interspeech.

See the program here
https://t.co/60pGWMgK9x

We are looking forward to seeing all of you there.

[Kyle Kastner @kastnerkyle]

Very proud to have been a (very tiny) part of this work on voice transfer for individuals with dysarthria, using zero-shot cross-lingual voice transfer https://t.co/keCHrJrf9r

[iseeaswell꩜bʂky @iseeaswell]

Excited to announce that 110 languages got added to Google Translate today! Time for context on these languages, especially the communities who helped a lot over the past few years, including Cantonese, NKo, and Faroese volunteers. Also, a 110-language youtube playlist. 🧵

[Shinji Watanabe @shinjiw_at_cmu]

Hi all,

This is the third call for papers about the SynData4GenAI workshop.

Good news!
While the submission data was originally due on June 18th, we'll extend it to June 24th.

Please submit your papers at https://t.co/fQiMCRnTWY
We look forward to your submissions!

[Shinji Watanabe @shinjiw_at_cmu]

This is the second call for papers about the SynData4GenAI workshop. Please mark your calendar for the submission due date (June 18, 2024, after the Interspeech acceptance notification)!

I'm also pasting the CFP.

[Ankur Bapna @ankurbpn]

2m tokens = ~2 hours of video or ~20!! hours of audio for anyone counting..

[Misha Teplitskiy | Science of Science @MishaTeplitskiy]

Lots of people in CS are (almost surely) GPT-ing their peer reviews
https://t.co/bICmqlunNA

[Shinji Watanabe @shinjiw_at_cmu]

Hi all,
We want to announce the new Interspeech satellite workshop called SynData4GenAI (Synthetic Data's Transformative Role in Foundational Speech Models).
Please check the details!
https://t.co/60pGWMgK9x

@ISCAInterspeech

[Kyle Kastner @kastnerkyle]

Robust multi-lingual TTS, which is effective on ASR-quality data. Taka (Takaaki Saeki) has several cool papers in this line, and now I get to be a part of one! Really proud of this work.

For more on arxiv: https://t.co/5iCOOk1VRv , and the samples page from Gary in the link

[Gary Wang @garygarywang]

Excited to share recent work on learning robust TTS from low quality data, ie TTS from 15 minutes of Fleurs! Samples here: https://t.co/cJqBP3RiDa, work spearheaded by intern turned Noogler Taka, and with @kastnerkyle @heiga_zen @andrewmaxr and others! Give it a read!

[Jessica Rosenkrantz @nervous_jessica]

Hello everyone! I have just posted Nervous System's annual seconds and prototypes sale puzzles in our Etsy shop. We save up all our "oopsie" and test puzzles for one big sale every year where you can get many of our designs at steep discounts. https://t.co/rXpQ0O1GKZ

[Google AI @GoogleAI]

Discover how Google Research is working to extend speech, translation, and language processing technologies to the 1,000 most spoken languages in the world in this lightning talk hosted by Uche Okonkwo and Sandy Ritchie at Research@ NYC → https://t.co/icjZydT3rC

[Julian Salazar @JulianSlzr]

Hiring a Student Researcher @GoogleAI this summer to work on long-form speech audio generation (data, modeling, evals) in Mountain View, California! 🗣️💬💬💬💬💬💬👂

Apply at https://t.co/wq5xav4hst and let me know ([email protected]) by Feb. 4.

The ideal candidate... [1/3]

[Jessica Rosenkrantz @nervous_jessica]

Shop small! Shop weird! Shop nerdy!
Shop artsy! Give the gift of @nervous_system jewelry (take 15% off with coupon HOLIDAY23) https://t.co/spx34HlB41