Tessera
Folgen

Martijn Bartelds

@mbartelds.bsky.social

Researcher at Together AI | Formerly at Stanford NLP, University of Groningen, TU Delft and UPenn

16 Posts420 Follower125 Folgt
Kaitlyn Zhou@kaitlynzhou.bsky.social · 3mo ago

Voice "cloning" is style transfer. Across three widely used systems — ElevenLabs V3, Coqui-XTTS, Chatterbox — clones don't just copy speakers, they reshape them to be warmer, more authoritative, more native English-like, and even more “humanlike”.

Martijn Bartelds@mbartelds.bsky.social · 7mo ago

Accepted at #ICLR2026! 🎉🇧🇷 Deep learning models often fail on specific subgroups. Group DRO was designed to help, but fails when group losses aren't comparable. This is common in speech. We introduce CTC-DRO: up to 47.1% lower worst-language errors in multilingual ASR 👇

Martijn Bartelds@mbartelds.bsky.social · last yr.

🎙️ Speech recognition is great - if you speak the right language. Our new @stanfordnlp.bsky.social paper introduces CTC-DRO, a training method that reduces worst-language errors by up to 47.1%. Work w/ Ananjan, Moussa, @jurafsky.bsky.social, Tatsu Hashimoto and Karen Livescu. Here’s how it works 🧵

Martijn Bartelds@mbartelds.bsky.social · 12mo ago

✨Meet OLMoASR✨ By pairing our curated 1M-hour dataset with a powerful architecture, we've built open ASR models that achieve competitive performance with models like Whisper. We're open-sourcing data, code and models to help the community build more robust and transparent ASR.

Ai2@ai2.bsky.social · 12mo ago

🎙️ Say hello to OLMoASR—our fully open, from-scratch speech-to-text (STT) model. Trained on a curated audio-text set, it boosts zero-shot ASR and now powers STT in the Ai2 Playground. 👇

Anastasia Koloskova@koloskova.bsky.social · last yr.

I am excited to announce that I will join the University of Zurich as an assistant professor in August this year! I am looking for PhD students and postdocs starting from the fall. My research interests include optimization, federated learning, machine learning, privacy, and unlearning.

Bild
Stanford NLP Group@stanfordnlp.bsky.social · 2y ago

Natural Language Processing—artificial intelligence that uses human language—has been on a roll lately. You’ve probably noticed! So the Stanford NLP Group has been growing, and diversifying into lots of new topics, including agents, language model programs, and socially aware #NLP. nlp.stanford.edu

Group picture of people in the Stanford NLP Group gathered in front of the shores of Lake Tahoe.
Martijn Bartelds@mbartelds.bsky.social · 2y ago

Excited to announce the launch of our ML-SUPERB 2.0 challenge @interspeech.bsky.social 2025! Join us in pushing the boundaries of multilingual ASR and LID! 🚀 💻 multilingual.superbbenchmark.org

SUPERB: Speech processing Universal PERformance Benchmark

A comprehensive and reproducible benchmark for Self-supervised Speech Representation Learning

multilingual.superbbenchmark.org

Shinji Watanabe@shinjiw.bsky.social · 2y ago

We are excited to announce the launch of ML SUPERB 2.0 (multilingual.superbbenchmark.org) as part of the Interspeech 2024 official challenge! We hope this upgraded version of ML SUPERB advances universal access to speech processing worldwide. Please join it! #Interspeech2025