Piotr Zelasko keynote on this very topic ! The model being released, as delivers his keynote.
Meet NVIDIA Nemotron 3.5 Transcribe 🎙️
An open-weight, promptable 30B MoE model with ~4B active parameters that brings transcription in 40 languages, speaker attribution, translation, contextual prompting and audio understanding into one checkpoint.
Watch it keep track of who said what when everyone’s talking at once.
1/ 🧵
13
We have Piotr Zelasko delivering keynote now on From Canary to Nemotron: Teaching Speech Models to Follow Instructions.
Afternoon session starts with keynote by Sebastian Möller on Evaluation of speech and language quality in the era of large speech and large language models.
Join us in F9-10!
Third keynote happening right now by Gabriel Skantze on Real-time coordination between humans and conversational agents !
Our second keynote of the day by @berraksismann is ongoing now !
Do grab your seat at F9-10 !
🎙️ Meet the #SALMA2026 keynote speakers!
Join us at #EMNLP2026 in Budapest on Wed, Oct 28 for talks by Philipp Koehn, Berrak Sisman, Gabriel Skantze, Sebastian Möller, Piotr Żelasko & Julia Hirschberg.
📅 Program: salma-workshop.github.io/sal…
🚨 SALMA 2026 ARR Commitment Deadline: August 26, 2026
Have a paper related to speech and audio language models, with existing ARR reviews? Commit your paper to SALMA.
CFP: salma-workshop.github.io/sal…
Link: openreview.net/group?id=EMNL…
#NLProc #EMNLP #ARR #Speech #Audio
🤖 Made with AI
🚨 Less than 2 weeks remain to submit to #SALMA2026!
📍 Co-located with #EMNLP2026
🗓️ Direct submission deadline: July 27, 2026
⏰ 11:59 PM UTC−12 (Anywhere on Earth)
Submit: openreview.net/group?id=EMNL…
Website: salma-workshop.github.io/sal…
1
59
📢 Call for Papers is out - salma-workshop.github.io/sal…
We invite submissions to SALMA 2026: Speech and Audio Language Models Workshop, co-located with EMNLP 2026.🎙️
🗓️ Direct Submission: July 27, 2026
ARR Commitment: August 26, 2026
Please spread the word and consider submitting!
🤖 Made with AI














