Hacker News Reader

Comment by guiriduro | Hacker News Reader

Oddly, I found the RNNoise suppression more distracting than the less sophisticated Speex suppressor. If you'll forgive the figurative language; compared with the noisy tracks, speex de-emphasises the noise into a quieter but smoother robotic 'bokeh', which allowed me to concentrate on the main speakers.

RNNoise on the other hand seemed to detect silences well, but left artifacts in the speech such that it had a choppy and artificial feel. Lacking the smoothness in the background I found I was more distracted by the distortions in the words.

View on HN

Interesting -- and unexpected. I also wrote the Speex suppressor and one of the things that specifically annoyed me about it was the robotic noise and the pseudo-reverberation it adds to the speech, but it seems like some people (like you) like that. Trying to understand exactly what you don't like about RNNoise... is it how the remaining background noise sounds or how sharply it turns on/off?

I did a quick hack to RNNoise to smooth out the attenuation and prevent it from cancelling more than 30 dB. I'd be curious if it improves or makes things worse for you (compared to the samples in the demo): https://jmvalin.ca/misc_stuff/rnn_hack1/

Subjectively it seems to me that the RNNoise sample doesn't trigger my brain to attempt to fill in the gaps.

With the Speex/raw ones I have all the data so if I listen to it again over and over I can get more out of it eventually.

With the RNNoise one I obviously don't even have enough extra data to even try doing that so all I can do is blame the algorithm.

Perhaps what you really want is an algorithm that lets through a bit more of the 'possible noise' for the human brain to have another go at.

What you're describing is more or less why noise suppression algorithms in general cannot really improve intelligibility of the speech. Unless they're given extra cues (like with a microphone array), there's nothing they can do in real-time that will beat what the brain is capable of with "delayed decision" (sometimes you'll only understand a word 1-2 seconds after it's spoken). So the goal of noise suppression is really just making the speech less annoying when the SNR is high enough not to affect intelligibility.

That being said, I still have control over the tradeoffs the algorithm makes by changing the loss function, i.e. how different kinds of mistakes are penalized.

Perhaps being more lenient in noisier situations could be an interesting tradeoff then. At lower noise levels it's already pretty good...

I think the biggest issue for me was the sharpness of the cutoff -- it actually sounded like a simple noise gate to me. The hack here helps a lot in smoothing out the sharp attack.

I found terminal sounds, fricatives and sibilants to be at a mininal distracting with RNN for "car" and "street", and at worst unintelligable. In particular, the terminal sound in "Christmas" was completely lost in the noise for me at 10dB with RNN, but was perfectly fine in Speex.

For "car" RNN sounded as good or better than Speex at all noise levels.

That rnn_hack is significantly better for me. 5dB on that sounds strictly better than 10dB on the original to my ear for "babble" and "street". I also noticed that the for the parts that sound the worst to me at 10-15dB in the original RNN, the signal is completely missing in the 0dB RNN version, so perhaps the signal is in the same band as the noise at that part?

Either way it's a tough tradeoff because I suspect that low bitrate encodings will love the nearly empty signal in the bands that are generated by the original, but the seemingly rectangular cutoff/introduction of the noise was much more jarring to me than the reverberation added by Speex (though I didn't like that in Speex, it didn't seem to add to my effort to understand the way that.

I also much prefer the Speex version. The robotic noise is consistent and easy to ignore. The NN version has a "choppy" feel to it that catches my attention. It reminds me of H264 vs VP9 video codecs at the same bitrate. VP9 is supposed to be better, but H264 artifacts are more artificial looking. VP9 artifacts look more natural, almost like mold/decay on film, which I find more distracting.

I prefer your hacked RNNoise version to the original, but I still prefer the Speex version. Robotic is predictable, and predictable is good. I don't want denoising artifacts to feel like there's some intelligent agent behind them, just as I don't want any software tool to feel intelligent. The smarter the tool the more jarring it is when it misreads my intentions. It might help average performance but it harms worst-case performance, and worst-case performance is subjectively more important because humans pay attention to outliers.

FWIW I much prefer the RNNoise version to the Speex version. With the Speex version the nosie is much more consistently present/noticeable/distracting.

It reminds me of the introduction of line noise into VoIP systems to replicate the natural electrical noise present in POTS systems. Without something, the hard attenuation brings more attention to the noise that still exists.

> a choppy and artificial feel.

To me it sounds like the kind of flange-y wafty MP3 glitches you used to get. At 0dB on the babble sample, it's painful to listen to whilst Speex is perfectly fine.

For me, Speex wins on all samples.

I didn't do any technical analysis, but to me RNN sounded as if they had just cut all noise between the narrators speech, and played all sound during their words, giving you a sharp amplitude difference and "stabbing" sensation.

At least that's my take on why Speex is subjectively more pleasant, with which I agree.

That's it, yeah, a kind of gated ramp effect at the beginning and end of words.

That means if they had access to the gate we can change that to our taste. Hope that is an option in the function.

Sounds like the difference between (e.g. soft-knee) compression and a noise gate.

The Speex suppressor is subjectively much nicer in all babble scenarios, but in some scenarios the RNN is better. E.g. it really excels at 20db car noise.

Personally i prefer speex even for car noise, as the rnn adds clicks and scratches that annoy me a lot more than more frequent soft distortions.

I didn't notice any issue with RNN at the lower levels of background noise, but as the background got noisier, I too heard what sounded like speaker distortion which seemed more distracting than the background noise.

I was slightly confused by the text that claimed that it was expected for the intelligibility to go down though, so maybe that's all working as intended.

Reply on news.ycombinator.com