SpeechBrain

#SpeechBrain is an all-in-one, open-source, PyTorch-based speech processing toolkit.

[SpeechBrain @SpeechBrain1]

It's great to have FocalCodec in SpeechBrain!

📄 Paper: https://t.co/Wy8y0NvGxJ
💻 Training Code (SpeechBrain): https://t.co/rDDgkaXwIc
🎧 Pretrained Model: https://t.co/i6poMR2EDM
🔊 Demo Samples: https://t.co/gujaTUHE5q

As always, true open-source, not just open weights!

[Mirco Ravanelli @mirco_ravanelli]

🚨 NeurIPS Alert!

FocalCodec: an ultra-low bit-rate #speech tokenizer for multimodal #LLMs. Simple, Compact, and meaning-preserving.

📄 Paper by Luca Della Libera: https://t.co/bEZ4nXgJo2

@Concordia @Mila_Quebec
#NeurIPS #AI #DeepLearning #OpenSource

[Mirco Ravanelli @mirco_ravanelli]

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: https://t.co/zQoPvinxHu

Please share!
#MLSP2025 #MachineLearning #SignalProcessing #DeepLearning #CallForPapers

[Mirco Ravanelli @mirco_ravanelli]

Huge thanks to @NVIDIAAIDev 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

[Convai_rg @convAI2024]

📢 Join our Conversational AI Reading Group!
📅 Thursday, March 13 | 11 AM - 12 PM EST
🎙Speaker: Alexandre Defossez @honualx
📖 Topic: "Moshi: a speech-text foundation model for real-time dialogue"
🔗 Details: (https://t.co/oxEZtl9zYt)

[Mirco Ravanelli @mirco_ravanelli]

#IEEE MLSP 2025 – Call for Papers

The OpenReview portal is now open!

📅 Deadline: April 22, 2025
🔗 Website: https://t.co/aQm0lJGfvW

We welcome #papers on #deeplearning, #speech/#audio, #LLMs, #CV, #NLP, #EEG, #optimization, #fintech, #healthcare, #wireless comms, & more!

[SpeechBrain @SpeechBrain1]

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: https://t.co/jVmfl49X86

[yingzhi wang @yingzhi_wang]

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:https://t.co/aihhVxLzqN
Github:https://t.co/qLefV92O7i

[SpeechBrain @SpeechBrain1]

@mirco_ravanelli @CemSubakan @Mila_Quebec @Concordia @IEEEsps @DSP_fact @slashML @IEEEorg @JResearchNews @ScienceNews The deadline for submitting special session proposals is fast approaching: February 1, 2025.

[Mirco Ravanelli @mirco_ravanelli]

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

https://t.co/S0Xvsm8gfA

[Mirco Ravanelli @mirco_ravanelli]

🌟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.

https://t.co/S0Xvsm8O58

#DeepLearning #AI #NeuralNetworks #Research

[Mirco Ravanelli @mirco_ravanelli]

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 @firatoncell discusses this issue.

📄 https://t.co/9zeQrPDPck

#AI #NLP #DeepLearning

[Mirco Ravanelli @mirco_ravanelli]

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: https://t.co/byRy5vyf64

The code will be available soon in #SpeechBrain.

#AI

[SpeechBrain @SpeechBrain1]

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

[Mirco Ravanelli @mirco_ravanelli]

#SpeechBrain-MOABB is an #opensource library for benchmarking #DeepLearning models on #EEG signals with a robust, reproducible protocol.

📢 News: Our #paper is published in Computers in #Biology and #Medicine!

📝 Paper: https://t.co/U9N2bTFR6J

💻 Code: https://t.co/gZ7MfEoplD

[SpeechBrain @SpeechBrain1]

Great work by @MousaviPooneh on discrete audio tokens, a key component for multimodal #LLMs.

Check out the #interspeech2024 paper:
https://t.co/8Pq3MY9bIf

Code now available in #SpeechBrain!

[Pooneh Mousavi @MousaviPooneh]

📢 I'll be presenting our paper "How Should We Extract Discrete Audio Tokens from Self-Supervised Models?" at InterSpeech! 🎙️

Meet us at the Speech Processing Using Discrete Speech Units, Oral Session on Sep 3, 16:20.

🔗 Paper: https://t.co/Z98B0DFjGD

#INTERSPEECH2024

[Mirco Ravanelli @mirco_ravanelli]

How can #LLMs improve the hypotheses generated by #ASR systems?

This interesting paper by @AdaDTur , just accepted to SLT 2024, explores this idea.

🔗 https://t.co/vsR6cs7kzF

#DeepLearning #Speech #Audio #LLM #Researchpaper #AI #MachineLearning

[SpeechBrain @SpeechBrain1]

Amazing work @Francesco 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

[francesco paissan @fpaissan_]

I am happy to announce that "Listenable Maps for Audio Classifiers" has been accepted at #icml2024 as an oral!

Check out
👨‍💻 code in @Speechbrain1 https://t.co/Pb0c0OHmwK
🖥️ website https://t.co/FRF4HVwvSE
📖 paper: https://t.co/BpKS0NGvoE

#AI #deeplearning #audio #explainableAI

[francesco paissan @fpaissan_]

I am happy to announce that "Listenable Maps for Audio Classifiers" has been accepted at #icml2024 as an oral!

Check out
👨‍💻 code in @Speechbrain1 https://t.co/Pb0c0OHmwK
🖥️ website https://t.co/FRF4HVwvSE
📖 paper: https://t.co/BpKS0NGvoE

#AI #deeplearning #audio #explainableAI

[Mirco Ravanelli @mirco_ravanelli]

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: https://t.co/JiRQJOqrDJ 🌐

#DeepLearning #researchpaper #AI

[Mirco Ravanelli @mirco_ravanelli]

The #IAPR Workshop on #NeuralNetworks in #PatternRecognition, known as #ANNPR2024, will occur this fall in Montreal at @Concordia.

More info: https://t.co/JiRQJOpTOb
Paper Submission: June 3, 2024.

Don't miss out on contributing!

#DeepLearning #AI #MachineLearning

[SpeechBrain @SpeechBrain1]

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:

https://t.co/2j5MSGK5qt

Explore all tutorials: https://t.co/CkYEluc8Lk

#AI