[Tutor] How to check whether audio bytes contain empty noise or actual voice/signal?

[marc nicole]

would this be helpful?
https://python-sounddevice.readthedocs.io/en/0.5.1/examples.html#plot-microphone-signal-s-in-real-time

Le sam. 26 oct. 2024 à 14:31, marc nicole <mk1853387 at gmail.com> a écrit :

> Thanks for the information.
>
> But what is a good way to look for presence of sound over the "background"
> from the audio data in Python 2.7?
>
> Thanks.
>
> Le sam. 26 oct. 2024 à 01:52, dn via Tutor <tutor at python.org> a écrit :
>
>> On 26/10/24 05:25, marc nicole via Tutor wrote:
>> > Hello Python fellows,
>> >
>> > I hope this question is not very far from the main topic of this list,
>> but
>> > I have a hard time finding a way to check whether audio data samples are
>> > containing empty noise or actual significant voice/noise.
>> >
>> > I am using PyAudio to collect the sound through my PC mic as follows:
>> >
>> > FRAMES_PER_BUFFER = 1024
>> > FORMAT = pyaudio.paInt16
>> > CHANNELS = 1
>> > RATE = 48000
>> > RECORD_SECONDS = 2import pyaudio
>> > audio = pyaudio.PyAudio()
>> > stream = audio.open(format=FORMAT,
>> >                  channels=CHANNELS,
>> >                  rate=RATE,
>> >                  input=True,
>> >                  frames_per_buffer=FRAMES_PER_BUFFER,
>> >                  input_device_index=2)
>> > data = stream.read(FRAMES_PER_BUFFER)
>> >
>> >
>> > I want to know whether or not data contains voice signals or empty
>> sound,
>> > To note that the variable always contains bytes (empty or sound) if I
>> print
>> > it.
>> >
>> > Is there an straightforward "easy way" to check whether data is filled
>> with
>> > empty noise or that somebody has made noise/spoke?
>>
>> If it were "easy" then there would be articles and tutorials aplenty...
>>
>> Signal processing is a very involved topic.
>>
>> A Fourier Transform can be thought of as converting a graph from signal
>> against time, to frequency components. Speech can then be identified.
>>
>> Filtering allows the inclusion/removal of unwanted frequencies (probably
>> not useful, per spec).
>>
>> Spectral Analysis is similar to above but with respect to changes over
>> time.
>>
>> Time-Domain analysis stays at the level of the current code. Try
>> graphing that. A lead-in period (of "silence") should enable
>> identification of background/technical noise. Perhaps thereafter, the
>> presence of sound over-and-above the "background" will be sufficient for
>> your purposes (use-case not stated).
>>
>> --
>> Regards,
>> =dn
>> _______________________________________________
>> Tutor maillist  -  Tutor at python.org
>> To unsubscribe or change subscription options:
>> https://mail.python.org/mailman/listinfo/tutor
>>
>