Heading to #Interspeech2025!
I’ll be involved in a tutorial, regular and special sessions (22 papers) & MLC-SLM workshop — and excited to chat about our new project: ESPnet3, CHiME-9, Urgent3, LARC, and YODAS++.
If you’re interested, come say hi — let’s collaborate! 🚀
@chimechallenge
⭐⭐ We are happy to announce the release of the tasks for the 9th CHiME Speech Separation and Recognition Challenge (CHiME-9).
⚡⚡ Please visit the CHiME Challenge website for details https://t.co/6MVwD7RKlv ⚡⚡
Hi all,
We have one month before the deadline! Please prepare the submission to our special issue "Multi-Speaker, Multi-Microphone, and Multi-Modal Distant Speech Recognition" at Computer Speech & Language.
https://t.co/xkaDBL7ypf
We're organizing a special issue at Computer Speech & Language about Multi-Speaker, Multi-Microphone, and Multi-Modal Distant Speech Recognition.
Deadline: December 2, 2024
https://t.co/sNDziQ3FQK
@chimechallenge
Deepen your expertise in speech processing at the 2024 CHiME Workshop! Join us at #INTERSPEECH2024 for a day of learning and collaboration with top experts. 📅 Sep 6, 2024, 🕗 8:00 – 17:00. Register now! https://t.co/NKdUlRYKH3 🌐 #AI#SpeechTech#MachineLearning
We'll have the CHiME-8 webinar! If you're interested in the CHiME-8 challenge, please join!
Date: May 20, 2024
Time: 8:00 AM (US - ET)
Place: https://t.co/bQG58I2McD
Join the CHiME8 pitching session on Monday, April 15th, at 17:30 at the HSCMA workshop venue (Room 205 at COEX, ICASSP venue).
The organizers of the three tracks of this year's edition will briefly introduce their tasks and answer questions.
We hope to see you there.
You might think speech recognition is "solved" with models such as @OpenAI’s Whisper, but it's not. Natural conversations with distant microphones still lack effective solutions.
To illustrate, on our newly released NOTSOFAR meeting benchmark, Whisper large-v3 with head-mounted mics achieves 9.3% WER (word-error-rate), yet on audio from a distant mic it climbs to 37.4% WER. The culprits are reverberation, noise, and overlapping speech, which interfere with the source signal.
What's the missing ingredient? We believe it's datasets.
The problem is not amenable to web scraping. Benchmarking datasets are scarce given their complex collection process. Microphone arrays, useful for speech separation, are rarely featured in labeled datasets, necessitating simulation to teach neural networks to utilize such arrays.
To bridge the gap our team at @Microsoft has released a benchmarking dataset of 280 recorded meetings, and a 1000-hour simulated training set synthesized for real-world generalization.
Join our challenge "NOTSOFAR: Distant Meeting Transcription with a Single Device", part of CHiME-8, to explore these resources and advance the field.
Details and registration: https://t.co/llTTzIXgQ9
Code and datasets: https://t.co/OAWwisO3Z9
📢⭐️⭐️⭐️@chimechallenge
We are pleased to announce that the leaderboard for the tasks is now available online and can be accessed at: https://t.co/0Vl9vRLb1V.
Additionally, the teams have refined the baselines.
It gives us great pleasure to pre-announce the 8th CHiME Speech Separation and Recognition Challenge (CHiME-8) that will launch in February 2024.
CHiME-8 TASKS includes:
Task 1 - DASR
Task 2 - NOTSOFAR-1
Task 3 - MMCSG
Please check https://t.co/rhQiJtrdWe
The final results for the CHiME-7 Task 1 (Distant Meeting Transcription with Multiple Devices) are out: https://t.co/vDryIZCd1V
Congratulations and many thanks to all participants 🎉, it was an arduos challenge (baseline was ~ on par with Whisper large in sub-track). (1)
The CHiME workshop was finished with great success! Thanks, everyone, for the excellent presentations and discussions! Please remember that the task proposal deadline is September 25th!
Listening test results and audio examples are out on the challenge website!
Congratulations to the Northwestern Polytechnical University and ByteDance team for winning, and many thanks to all participants!
We'll soon provide a further analysis of the results.
@chimechallenge