Re: [AUDITORY] Cut silence in beginning and end of speech recordings automatically?

[Gabriele Bunkheila <gbunkhei@xxxxxxxxxxxxx>]

Hi Tamar,

 

Since you mentioned MATLAB, I thought I’d share a couple of pointers. A good fit for this would be detectSpeech (https://www.mathworks.com/help/audio/ref/detectspeech.html), which uses a fairly accessible algorithm based on short-term energy and spectral spread. detectSpeech has been available in Audio Toolbox since release R2020a.

 

In case any of your data was more challenging, you could consider trying the function classifySound (https://www.mathworks.com/help/audio/ref/classifysound.html), which has only been available since release R2020b and uses the pre-trained YAMNet network under the hood.

 

I hope this helps – feel free to get in touch directly if you needed more guidance.

Regards and good luck,
Gabriele.

 

--

Gabriele Bunkheila [he/him] – Product Management, DSP and Audio

MathWorks

 

From: AUDITORY - Research in Auditory Perception <AUDITORY@xxxxxxxxxxxxxxx> On Behalf Of Tamar Regev
Sent: miércoles, 3 de marzo de 2021 16:10
To: AUDITORY@xxxxxxxxxxxxxxx
Subject: [AUDITORY] Cut silence in beginning and end of speech recordings automatically?

 

Hi all,

 

Does anyone know of a good way to automatically trim silent parts (which may contain some minor background noise) at the beginning and end of speech recordings?

 

Preferentially using Matlab but any other automatic way would work (we want to run this on many sound files).

 

Thanks a lot!

Tamar