Hi,

does anyone knows of good audio denoising software for Linux
(OpenSource)?

Thank you very much in advance for any help!

Have a nice weekend!
Best regards,
mcc

On Fri, Dec 9, 2011 at 1:46 PM, <meino.cramer@gmx.de> wrote:
> Hi,
>
> does anyone knows of good audio denoising software for Linux
> (OpenSource)?
>
> Thank you very much in advance for any help!

I'm not an audio professional with experience with different tools, so
I couldn't tell you if it's necessarily "good", but Audacity has a
noise filter. Select a range in your sample that consists of nothing
*but* noise, and tell it to collect a noise profile. Then select your
entire sample, and then have it apply the profile to remove that
noise.

Obviously, the poorer your S/N ratio is to begin with, the worse your
results will be.

--
:wq

on 2011-12-09 at 13:55 Michael Mol wrote:

>I couldn't tell you if it's necessarily "good", but Audacity has a
>noise filter.

that's exactly what i was about to reply.

and if you want to try a CLI tool, sox provides a similar utility.

noiseprof [profile-file]
Calculate a profile of the audio for use in noise reduction.
See the description of the noisered effect for details.

noisered [profile-file [amount]]
Reduce noise in the audio signal by profiling and filtering. This
effect is moderately effective at removing consistent background
noise such as hiss or hum. To use it, first run SoX with the
noise� prof effect on a section of audio that ideally would contain
silence but in fact contains noise - such sections are typically
found at the beginning or the end of a recording. noiseprof will
write out a noise profile to profile-file, or to stdout if no
profile-file or if `-' is given. E.g. sox speech.wav -n trim 0 1.5
noiseprof speech.noise-profile To actually remove the noise, run
SoX again, this time with the noisered effect; noisered will
reduce noise according to a noise profile (which was generated by
noiseprof), from profile-file, or from stdin if no profile-file or
if `-' is given. E.g. sox speech.wav cleaned.wav noisered
speech.noise-profile 0.3 How much noise should be removed is
specified by amount-a number between 0 and 1 with a default of
0.5. Higher numbers will remove more noise but present a greater
likelihood of removing wanted components of the audio signal.
Before replacing an original recording with a noise-reduced
version, experiment with different amount values to find the
optimal one for your audio; use headphones to check that you are
happy with the results, paying particular attention to quieter
sections of the audio.

On most systems, the two stages - profiling and reduction
- can be combined using a pipe, e.g. sox noisy.wav -n
trim 0 1 noiseprof | play noisy.wav noisered

never compared the results, if you do, i for one would be very interested
in your experience.

IMO, it's much better to remove noise by small amounts in successive
passes (taking a new profile each time, of course), than trying to remove
too much noise in one pass.

let us know how it went!

lj

luis jure <ljc@internet.com.uy> [11-12-10 13:28]:
> on 2011-12-09 at 13:55 Michael Mol wrote:
>
> >I couldn't tell you if it's necessarily "good", but Audacity has a
> >noise filter.
>
> that's exactly what i was about to reply.
>
> and if you want to try a CLI tool, sox provides a similar utility.
>
> noiseprof [profile-file]
> Calculate a profile of the audio for use in noise reduction.
> See the description of the noisered effect for details.
>
> noisered [profile-file [amount]]
> Reduce noise in the audio signal by profiling and filtering. This
> effect is moderately effective at removing consistent background
> noise such as hiss or hum. To use it, first run SoX with the
> noise� prof effect on a section of audio that ideally would contain
> silence but in fact contains noise - such sections are typically
> found at the beginning or the end of a recording. noiseprof will
> write out a noise profile to profile-file, or to stdout if no
> profile-file or if `-' is given. E.g. sox speech.wav -n trim 0 1.5
> noiseprof speech.noise-profile To actually remove the noise, run
> SoX again, this time with the noisered effect; noisered will
> reduce noise according to a noise profile (which was generated by
> noiseprof), from profile-file, or from stdin if no profile-file or
> if `-' is given. E.g. sox speech.wav cleaned.wav noisered
> speech.noise-profile 0.3 How much noise should be removed is
> specified by amount-a number between 0 and 1 with a default of
> 0.5. Higher numbers will remove more noise but present a greater
> likelihood of removing wanted components of the audio signal.
> Before replacing an original recording with a noise-reduced
> version, experiment with different amount values to find the
> optimal one for your audio; use headphones to check that you are
> happy with the results, paying particular attention to quieter
> sections of the audio.
>
> On most systems, the two stages - profiling and reduction
> - can be combined using a pipe, e.g. sox noisy.wav -n
> trim 0 1 noiseprof | play noisy.wav noisered
>
> never compared the results, if you do, i for one would be very interested
> in your experience.
>
> IMO, it's much better to remove noise by small amounts in successive
> passes (taking a new profile each time, of course), than trying to remove
> too much noise in one pass.
>
> let us know how it went!
>
> lj
>

Thanks for all your replies !


In the net I read about audacities denoise and that it is not /that/
good. I didnt checked it myself though. At the same place "Gnome Wave
Cleaner" (gwc) was recommended instead of audacities denoiser. On its
homepage there is also linked a downloadable book about digital signal
processing (34 chapters) which looks quite proefessional.

Gwc is ... not the youngest software and development seems to have
stopped. Now I trying to get this beast working under Gentoo.
The alsa-problem with "snd_pcm_write" can be workarounded with
installing pulseaudio and playing the sound with gwc via pulseaudio
instead of with alsa directly.
While compiling gwc you need to enable alsa and pulseaudio with
./configure.

When gwc is running I wll report more.
See my other posting sent just before this one.

Gwc is the first denoise I will try.

Have a nice, denoised weekend!
Best regards,
mcc

luis jure <ljc@internet.com.uy> [11-12-10 13:28]:
> on 2011-12-09 at 13:55 Michael Mol wrote:
>
> >I couldn't tell you if it's necessarily "good", but Audacity has a
> >noise filter.
>
> that's exactly what i was about to reply.
>
> and if you want to try a CLI tool, sox provides a similar utility.
>
> noiseprof [profile-file]
> Calculate a profile of the audio for use in noise reduction.
> See the description of the noisered effect for details.
>
> noisered [profile-file [amount]]
> Reduce noise in the audio signal by profiling and filtering. This
> effect is moderately effective at removing consistent background
> noise such as hiss or hum. To use it, first run SoX with the
> noise� prof effect on a section of audio that ideally would contain
> silence but in fact contains noise - such sections are typically
> found at the beginning or the end of a recording. noiseprof will
> write out a noise profile to profile-file, or to stdout if no
> profile-file or if `-' is given. E.g. sox speech.wav -n trim 0 1.5
> noiseprof speech.noise-profile To actually remove the noise, run
> SoX again, this time with the noisered effect; noisered will
> reduce noise according to a noise profile (which was generated by
> noiseprof), from profile-file, or from stdin if no profile-file or
> if `-' is given. E.g. sox speech.wav cleaned.wav noisered
> speech.noise-profile 0.3 How much noise should be removed is
> specified by amount-a number between 0 and 1 with a default of
> 0.5. Higher numbers will remove more noise but present a greater
> likelihood of removing wanted components of the audio signal.
> Before replacing an original recording with a noise-reduced
> version, experiment with different amount values to find the
> optimal one for your audio; use headphones to check that you are
> happy with the results, paying particular attention to quieter
> sections of the audio.
>
> On most systems, the two stages - profiling and reduction
> - can be combined using a pipe, e.g. sox noisy.wav -n
> trim 0 1 noiseprof | play noisy.wav noisered
>
> never compared the results, if you do, i for one would be very interested
> in your experience.
>
> IMO, it's much better to remove noise by small amounts in successive
> passes (taking a new profile each time, of course), than trying to remove
> too much noise in one pass.
>
> let us know how it went!
>
> lj
>

I have some results now. "Measurement" was only done with my two ears
in a before/after-way of doing. No spectrum analysis or other high
advanced stuff.

Device: Recording was done with a Tascam DR2D field recorder (SDcard
recordings), which has a nice sound and a fine stereo image ... and a
slightly high noise floor.

Test:
I set the internal mics of the Tascam to mid
gain and pushed the level to max. I think (read: "I dont know for
sure") that the level is simply a variable resistor in the signal
path. The gain is the amplification level...so the noise comes from
this source beside others. No AGC was active.

I went into the kitchen, put the recorder on the desk and switch it
on. I let it record its own noise for a moment or two and then start
to boil water (high freqs in the sound) and I produced other sounds
which contain high freqs.

After a while I stopped recording.

As exspected, the recording was filled with some noise, which was not
destructive but fairly audible.

I loaded the file into audacity, and used the denoising filter.
The result has noticeable less noise but it was still audible.

Then I used gwc in conjunction with pulseaudio. I leave all the setting
alone and only selected for the Window function "Hanning-overlap-add"
and for the Noise Suppression Method "Lober & Hoeldrich", both marked
with "Best" in the settings menu.

I denoised the same input as above.

The result? There was no noise at all anymore -- at least for my ears.
Both files were checked using earphones and played with the Tascam
instead being played through the PC loudspeakers.
In the beginning of the file there were some audible artifacts, which
may result from too less read data...but this is guessed.

Gwc is a little fragile due the longer period it was not maintained
anymore. Its alsa interface simply does not work.

But it clearly wins when it comes to denoising. It also supports the
removal of other audio artifacts.

HTH!
Best regards,
mcc

on 2011-12-10 at 20:50 meino.cramer@gmx.de wrote:

>Gwc is a little fragile due the longer period it was not maintained
>anymore. Its alsa interface simply does not work.
>
>But it clearly wins when it comes to denoising. It also supports the
>removal of other audio artifacts.

vielen dank für den bericht, meino! :-)

yes, i remember gwc from the old days, but i hadn't heard from it for a
long time... it's a pity that it has been abandoned, but the same happened
with many audio applications for linux.

i wonder if the algorithms could be implemented as audacity plugins?

alles gute,

lj