🚀🎉 #SpeechBrain 1.0 introduces a bunch of methods for continual #deeplearning. We're happy to announce the CL-MASR benchmark, designed to facilitate the continual #deeplearning of new languages for #SpeechRecognition. Explore more at: github.com/speechbrain/be… #AI #opensource

🚀 SKILL is #deeplearning method for distilling knowledge from SSL models! 💡 Unlike traditional methods, SKILL distills across layer groups. Check out our paper presented at #ICASSP-#SAAB: arxiv.org/abs/2402.16830 Collaborative effort with EPFL and Sony. Luca Zampierin #AI

Quantization plays a crucial role in #deeplearning. It speeds up your model and reduces its memory footprint. Curious about how to implement it with #SpeechBrain? Check out Justin Lam's #tutorial: colab.research.google.com/drive/1IoxCu_h… Explore all tutorials: speechbrain.github.io #AI

The #IAPR Workshop on #NeuralNetworks in #PatternRecognition, known as #ANNPR2024, will occur this fall in Montreal at Concordia University. More info: users.encs.concordia.ca/~annpr24/ Paper Submission: June 3, 2024. Don't miss out on contributing! #DeepLearning #AI #MachineLearning

With the #NeurIPS2024 deadline behind us, it's time to start working on our next paper. ✍️ We are organizing #ANNPR2024 in Montreal at Concordia University. 🍁 The submission deadline is June 3rd. Details: users.encs.concordia.ca/~annpr24/ 🌐 #DeepLearning #researchpaper #AI

I am happy to announce that "Listenable Maps for Audio Classifiers" has been accepted at #icml2024 as an oral! Check out 👨‍💻 code in @Speechbrain1 tinyurl.com/lmac-code 🖥️ website tinyurl.com/lmac2 📖 paper: tinyurl.com/lmac5 #AI #deeplearning #audio #explainableAI

Amazing work Francesco Fornaro and Cem. The paper will be presented in an oral session at #iclm2024 and the code is available in #SpeechBrain! #deeplearning #AI #Audio #MachineLearning #NeuralNetworks

How can #LLMs improve the hypotheses generated by #ASR systems? This interesting paper by @AdaDTur , just accepted to SLT 2024, explores this idea. 🔗 arxiv.org/abs/2409.00217 #DeepLearning #Speech #Audio #LLM #Researchpaper #AI #MachineLearning

Great work by Pooneh Mousavi on discrete audio tokens, a key component for multimodal #LLMs. Check out the #interspeech2024 paper: arxiv.org/pdf/2406.10735 Code now available in #SpeechBrain!

A long-term goal of #SpeechBrain is to enable natural human-machine communication, including #EEG support. #SpeechBrain-MOABB is a key first step in this direction, and it is now supporting EEG decoding tasks like motor imagery and more! #SpeechBrain #EEG #AI #DeepLearning

This #NeurIPS2024 paper, co-authored with Francesco Paissan, Luca Della Libera, and Cem Subakan, is another step toward more interpretable #deeplearning for #audio classifiers. Read the paper here: arxiv.org/pdf/2405.17615 The code will be available soon in #SpeechBrain. #AI

Fine-tuning #LLMs on domain-specific data doesn’t always improve performance, a challenge we call the "Adaptation Odyssey". Why does this happen? Our new #EMNLP2024 paper led by Firat Oncel discusses this issue. 📄 arxiv.org/pdf/2410.05581 #AI #NLP #DeepLearning

🌟To all #MachineLearning researchers: Join us in #Istanbul for the 35th #IEEE MLSP 2025 📅 Aug 31–Sept 3, 2025 We’re working hard to make this a memorable event in one of the world's most beautiful cities. 2025.ieeemlsp.org/en/ #DeepLearning #AI #NeuralNetworks #Research

We are working hard to organize the 35th #IEEE #MachineLearning for #SignalProcessing Workshop (MLSP) in #Istanbul (Aug 31–Sept 3, 2025)! It will be an unforgettable event with inspiring #research, talks, and keynotes. Paper submissions: Apr 22, 2025 2025.ieeemlsp.org/en/

Our Speech-LLM diagnosis paper "What Are They Doing? Joint Audio-Speech Co-Reasoning" is accepted at #ICASSP 2025. Your model behaves more like an Audio-LLM or a Speech-LLM? See our specially designed task and dataset: Paper:arxiv.org/pdf/2409.14526 Github:github.com/BenoitWang/Wha…

My lab is running an amazing Reading Group on #ConversationalAI, open to all! This week (Feb 6, 11 AM EST) we host Hung-yi Lee, a top #AI researcher! He’ll talk about: "Teaching Foundation Models New Skills: Insights and Experiences". 🌍 Website: poonehmousavi.github.io/rg.html

📢 Join our Conversational AI Reading Group! 📅 Thursday, March 13 | 11 AM - 12 PM EST 🎙Speaker: Alexandre Defossez Alexandre Défossez 📖 Topic: "Moshi: a speech-text foundation model for real-time dialogue" 🔗 Details: (poonehmousavi.github.io/rg)

#IEEE MLSP 2025 – Call for Papers The OpenReview portal is now open! 📅 Deadline: April 22, 2025 🔗 Website: 2025.ieeemlsp.org We welcome #papers on #deeplearning, #speech/#audio, #LLMs, #CV, #NLP, #EEG, #optimization, #fintech, #healthcare, #wireless comms, & more!

Huge thanks to NVIDIA AI Developer for the NVIDIA Academic Grant #NVIDIAGrant! My team is already using the donated GPU hours on Saturn Cloud to accelerate our research. So grateful! #research #AI #SpeechBrain #GPU #A100 #DeepLearning #OpenSource #NVIDIA

Deadline Extended !!! The paper submission deadline for #IEEE MLSP 2025 is now April 29, 2025. We hope this gives more authors the chance to contribute! More info: 2025.ieeemlsp.org/en/CALL-FOR-PA… Please share! #MLSP2025 #MachineLearning #SignalProcessing #DeepLearning #CallForPapers