Saw this on Emma Strubell’s (not on Twitter?) office door today. It is only computer!

22 papers were accepted at Interspeech'25! See you soon in Rotterdam!

🎵💬 If you are interested in Audio Tokenisers, you should check out our new work! We empirically analysed existing tokenisers from every way - reconstruction, downstream, LMs and more. Grab yourself a ☕/🍺 and sit down for a read!

Not advertised yet, but we figured out how to do this too. And we release how exactly you can do it 👀. With the right training techniques, you can inject audio understanding and generation into an LLM with almost no loss in text perf. Details at arxiv.org/abs/2506.17611

Meows, music, murmurs and more! We train a general purpose audio encoder and open source the code, checkpoints and evaluation toolkit.

📢 Excited to announce our 2-day workshop on "Foundations of Speech and Audio Foundation Models" at TTI Chicago, happening September 4–5! 🔗 Info & registration: sites.google.com/view/speech-ai… 📝 Poster submissions welcome! Join us for talks, discussions, and community building!

I will be presenting 3 papers from WAVLab | @CarnegieMellon at #Interspeech2025 🇳🇱 One is OWSMv4 (led by Yifan Peng), nominated for best student paper isca-archive.org/interspeech_20… It focuses a lot on data cleaning, particularly for non-English languages It will be an oral on Tues 15:10 at dock 10B.

Our work on OWSM v4 received the Best Student Paper Award at #Interspeech2025! 🏆🎉 Huge congratulations to the team! 🚀👏 I’m especially happy to see our open science efforts for speech foundation models recognized by the community. 🙌 🔗 isca-archive.org/interspeech_20…

We got the #Interspeech2025 Best Student Paper award! Congrats to Yifan Peng, Muhammad Shakeel, Yui Sudo, Jinchuan Tian (田晋川), and Chyi-Jiunn Lin!

Excited to receive the Best Student Paper Award at #Interspeech2025 I started the OWSM project in 2023. It took me great effort to design a robust and scalable training framework using ESPnet, prepare unified data formats, and conduct large-scale training with academic resources.