Khaled Koutini

Researcher @cpjku | Machine learning | Signal processing | Model compression | Adversarial Robustness.

[Khaled Koutini @kkoutini]

@gblazex @jxmnop @huggingface Thanks!

[Khaled Koutini @kkoutini]

@jxmnop @gblazex @huggingface I'm working on the PR https://t.co/tlBOJMx2C8 to make this the default behaviour, it should be merged soon!

[Sepp Hochreiter @HochreiterSepp]

Super excited about our adversarial models (not examples!) for uncertainty quantification. Model prediction is uncertain if other models with large posterior predict differently. Improved integral approximation by mixture importance sampling based on constraint optimization. Cool

[Ankit Shah @ankits0052]

Presented tutorial @ISCAInterspeech 2022 on learning from weak labels.
Overall it went well.
https://t.co/vcLDrDsGiR
#INTERSPEECH2022

[Annamaria Mesaros @AnnamariaMsros]

DCASE workshop submission system is finally open!

[Benjamin Elizalde @benjaminelizal]

Our CLAP 👏 model learns audio concepts from natural language supervision. CLAP achieves SoTA in Zero-Shot learning for different audio tasks. For example, in ESC50 CLAP achieves 82% acc, better than human classification with 81%. https://t.co/gLeaO9GujN

[HEAR Benchmark @hearbenchmark]

HEAR PMLR journal submissions are open until 2022-06-30. https://t.co/URhf1PPgrY

Besides that, people have asked if they can run HEAR benchmarks, get on the leaderboard, cite us in the future. Yes! HEAR is here to stay. See our updated website: https://t.co/VuSnPYF095

[Pieter-Jan Hoedt @ml_hoedt]

In case you missed it: I am one of the contributors to the first ICLR blog post track this year! I (tried to) write about Normalizer-Free networks (https://t.co/P6AbpDYlQA) and what they can and can not tell us about normalization:

https://t.co/DsJTo80K4v

[Austrian Artificial Intelligence Podcast @aaip_podcast]

Thank you @heghbalz for appearing on the podcast and talking about your research on robust and disentangled representations.

https://t.co/cC9drKMWF6

[Khaled Koutini @kkoutini]

Checkout the pre-print on arxiv https://t.co/nJRRkOuXJW
and the source code https://t.co/xXowr3qPjj
Joint work with Jan Schlüter, @heghbalz and Gerhard Widmer.

[Khaled Koutini @kkoutini]

If you're attending @NeurIPSConf, don't miss today's Competition Track at 19:00 GMT. HEAR 2021 will be presented @neuralaudio.
I will give a lightning talk about our latest work "PaSST: Efficient Training of Audio Transformers with Patchout"
#NeurIPS2021

[Khaled Koutini @kkoutini]

If you're attending @NeurIPSConf, don't miss today's Competition Track at 19:00 GMT. HEAR 2021 will be presented @neuralaudio.
I will give a lightning talk about our latest work "PaSST: Efficient Training of Audio Transformers with Patchout"
#NeurIPS2021

[HEAR Benchmark @hearbenchmark]

We are pleased to share the HEAR 2021 challenge results

https://t.co/zLMxaBHnKw

[Eduardo Fonseca @edfonseca_]

🔊Here's the video presentation of our WASPAA21 paper: "Self-Supervised Learning from Automatically Separated Sound Scenes". Work done during an internship at Google Research.
paper: https://t.co/NvEhyI8BzE
video: https://t.co/TD2x6Gs9b8
slides: https://t.co/U0LcbcgjfC

[Yasaman Bahri @yasamanbb]

Join us tomorrow for our workshop "Overparameterization: Pitfalls & Opportunities":

[Eduardo Fonseca @edfonseca_]

New paper! We evaluate two pooling methods to improve shift invariance in CNNs, obtaining SOTA on FSD50K. Methods are based on low-pass filtering & adaptive sampling of feature maps. They increase robustness to time/freq shifts in the input! w/ @andrebola_ https://t.co/j1C4SviomM

[Hamid Eghbalzadeh @heghbalz]

And go check out @kkoutini et, al poster on Over-Parameterization and Generalization in Audio Classification!

📜: https://t.co/Q2iOHMJG5J

[Shreyan Chowdhury @shreyan_ch]

So many exciting papers accepted for @ismir2021! Can't wait for the conference!

Adding ours: "On Perceived Emotion in Expressive Piano Performance: Further Experimental Evidence for the Relevance of Mid-level Perceptual Features" w/Gerhard Widmer @cpjku

[Verena Praher @veroamilbe]

I am happy to announce that our latest work "On the Veracity of Local, Model-agnostic Explanations in Audio Classification: Targeted Investigations with Adversarial Examples" (together w/ @katxiip, Arthur Flexer and Gerhard Widmer from @cpjku) has been accepted to @ismir2021 🎉🥳

[Markus Schedl @m_schedl]

Very happy to announce a new #LIT project to start in fall @cpjku: Mitigating Gender Bias in Job Recommender Systems: A Machine Learning-Law Synergy (TIMELY). We are looking for PhD students in recommender systems, NLP, and non-discrimination. #HCAI #MMS #RecSys #NLP #RecSys2021

[Verena Praher @veroamilbe]

On Wednesday we are going to present our latest work "Tracing Back Music Emotion Predictions to Sound Sources and Intuitive Perceptual Qualities" at the Sound and Music Computing Conference in Session 8. See you there! @smcnetorg