📢 Barbara Schuppler (TU Graz) gives the 2nd #JSALT plenary tomorrow, Tue July 1, 11:00 in Room E112: "Cross-layer models for conversational speech recognition in low-resourced scenarios". Join in person or on YouTube: 🎤📺.

Our paper "Diarization-conditioned Whisper for target speaker automatic speech recognition” is out and the highlights include exploring various ways to biasing Whisper for target speaker ASR. The paper is available free of charge from ScienceDirect:.

Honza is giving a lecture at Charles University in Prague (Faculty of Mathematics and Physics, MFF) today. If you want to attend, note that it takes place in the new buildings of MFF in Troja, not the historical one in Mala Strana.

Talk will be streamed on youtube Abstract and speaker’s bio in

We have great pleasure to invite you to a talk of an excellent Czech scientist, Professor at #EPFL, Lenka Zdeborová. We have never seen a talk treating machine learning as a problem of statistical physics! Tuesday, May 20, 2025 at 13:00 in lecture room E112 and online.

Several speech students participated at the @FIT_VUT Conference of innovations, technology and science - Excel@FIT. Congratulations to Sathvik, Dominik, and Ondrej for winning Excel prizes!.

Congratulations to Lin Zhang for her new post-doc position @jhuclsp ! She is working on anti-spoofing and anonymization with Nicholas Andrews and Matthew Wiesner. She also collaborates closely with Sanjeev Khudanpur, Leibny Paola García-Perera, and Kevin Duh.

Over the weekend we to plan for the upcoming #JSALT25 workshop for the topic "Advancing Expert-Level Reasoning and Understanding in Large Audio Language Models". Two days of intense brain storming 🧠 and planning powered by extra portions of coffee ☕️.

The networking activities around ICASSP continued after Meeami: on Monday 7 April, Honza took part in an official visit to IIIT Hyderabad, met its director and spent nice time with Anil Kumar Vuppala and his colleagues and students in Language Technologies Research Center (LTRC).

Our research group continues its industry collaboration at global scale, with Santosh and Alex recently visiting Meeami Technologies in #Hyderabad, where they had engaging and insightful discussions! We thank Meeami for their hospitality and for a fantastic lunch at ITC Peshawar!

Continuing the #ICASSP25 publicity:.Leveraging Self-Supervised Learning for Speaker Diarization, by Jiangyu Han et al. Apr 9: 5:00 pm - 6:30 pm, Lecture, Room: MRG.04, Johan Rohdin (Jiangyu did not get Indian visa)

🗣️ We're now on Bluesky! Follow us there for updates and conversations: Looking forward to connecting! #BSKY.

A novel approach to training TS-ASR systems. 💡By conditioning on frame-level diarization outputs, our method preserves the model’s single-talker multilingual capabilities and performance, while enabling speaker attribution 🎉.

A bit of publicity for our papers to be presented at #ICASSP25 in Hyderabad!. Target Speaker ASR with Whisper, Apr 11: 2:00 pm - 3:30 pm, Poster 2E, presented by Alexander Polok

Music needs to be played even amidst research and JSALT preparations - Sylva and Honza will perform in a regular concert of their folklore band on April 11th. This time, some songs from Hornacko - a tiny region on Moravian-Slovak border with beautiful music 🎻🪈

🗣️ Are you participating in the #Interspeech2025 Workshop on Multilingual Conversational Speech Language Models organised by @nexdata_ai?. We’ve released our baseline model for the community ready for you to explore and build upon!.

Happy to announce new speech baby 👶 - Tamara Silnova was born last Monday and both she and mom are healthy and well. Big congratulations to Ania and Sergej!

RT @FIT_VUT: V pondělí 10. března bude obhajovat disertační práci: "Jazykové modely pro nedokonalé systémy rozpoznání řeči a písma" Karel….

For abstract 📜, see the official invitation

Lukas was Karel's supervisor and we are grateful to Matthew Wiesner, from @jhuclsp and to Marek Hrúz from the @ZapadoceskaUni for reviews.