Am I missing something?

Yet in AI research (which is essentially statistical modeling)we routinely abandon these basic practices. The irony is striking.

In other scientific fields (natural and social sciences), proper statistical analysis is fundamental. You simply cannot publish without it.

There's also the added problem that metrics often don't correlate with perception. A 0.1 dB SDR improvement might be meaningless perceptually. But this issue has been discussed more often than the statistical rigor problem.

❌ Claims of "superior performance" based on point estimates alone

Example: Paper A reports 15.21 dB, Paper B reports 15.01 dB. Is this difference meaningful or just noise? Do those decimal places have any meaning? Usually impossible to tell from the paper.

❌ Values without error bars/confidence intervals
❌ Standard deviations sometimes quoted but no uncertainty estimates of means
❌ No significance testing whatsoever
❌ No effect size analysis
❌ No exploratory analysis beyond the mean

We're not even applying methods from first-year undergraduate physics—like reporting results with error bars. The problems I regularly see would make any physics professor cringe.

This work was the result of Silvia Arellano's internship in Dolby Barcelona with us.

Come explore the demo here:
🔗 silviaarellanogarcia.github.io/rir-acoustic/
📄 Paper: arxiv.org/pdf/2507.12136

Feedback & questions welcome!

We explore 4 DAC-based models:
1️⃣ AR w/ cross-attention
2️⃣ AR w/ classifier guidance
3️⃣ MaskGIT w/ adaptive layer norm
4️⃣ Flow matching

The MaskGIT model achieves the best subjective quality (avg. 70 MUSHRA score), beating state of the art comparisons.

Instead of simulating room geometry, we train four different generative model to produce RIRs conditioned on acoustic attributes (T30, T15, EDT, D50, C80, source-receiver distance)

Last winner, Eloi Moliner, pioneered diffusion models in AI for audio restoration. Could you be next?

arxiv.org/abs/2210.15228

The key issue isn't the most likely outcome — it's the worst-case scenario we must be prepared for.

arxiv.org/abs/2401.02843

Just as nuclear research is subject to international oversight, frontier AI development should be too. We need strong global regulatory frameworks for models with potentially vast power.

www.iaea.org

Example audio samples here: metlosz.github.io/dealiasing_a...

Spatial aliasing occurs when microphone spacing in an array is too large relative to the wavelength of sound, degrading the accuracy of beamforming.

As far as we know, this is the first deep learning paper that addresses directly this problem (other approaches deal with this in an indirect way).