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

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

From: Boyang Qin <boyangqi@xxxxxxxxxxx>

Date: Fri, 5 Mar 2021 12:15:03 -0500

Arc-authentication-results: i=1; mx.google.com; spf=pass (google.com: domain of owner-auditory@xxxxxxxxxxxxxxx designates 132.206.27.103 as permitted sender) smtp.mailfrom=owner-auditory@xxxxxxxxxxxxxxx

Arc-message-signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-archive:list-owner:list-subscribe:list-unsubscribe:list-help :precedence:in-reply-to:to:comments:subject:from:sender:reply-to :date:message-id:references:mime-version:approved-by; bh=vmfUcIMT3Gsa9jFR9GSo1NGZrHmrgRd47SCW4EriSnk=; b=DF3ivL88FKu0p3lYCRdc872gtIJ3IArMRQwFghCUMluaYbxoZBMhEtcYbNhgGKL0NV 5D+G1QkwCqDR1zNhsPce5ScGuG5ZEUL89vHD55g9cTCrDVJwfXXxmfb4vP+Hmg5688hW Tua8FPtYDK+188DrriFfbRJZG9h/pS/qzPHAkeaD2Audenn2B8B0Ej07P5GT5zSF0Mnw dG6sfb0qSGoJPkVHnPnosARjCKX0RzBi7oz23PygiGNtDMcWptXxRzxM5Edi+aLw1gx9 u1/Ps6ar52gbcwXgc+vaKg4WGLgX/JEPu7fFOBxW4G/zp564vr+f+9YW6/hy76+0nRmH XSZQ==

Arc-seal: i=1; a=rsa-sha256; t=1615009084; cv=none; d=google.com; s=arc-20160816; b=c1S9F5A9HiS7ZECT7TdeSV8NdPYChqBgu9qW0+8JPTGOk6ayk/IrNNV8aj8F/97Cjs n63rstVz3n0t65NHbgehwDKJMxC2nYcEBrheGfOxdKyzY0nkd5s3E2iiy7zGRqua0B52 Yt6HYdAZSpoR016LKzOdqdWL1BGChbh07jRQzG65w7M5PY0O/ar1+AjqA+zcQ5ulMjg0 r4vcWWKtl8k+Bf0uvg22WIDIMZQId+MOuTdt6CMOHuyVRnMZSS+XhMmOcHMfpA3N1bCn f6KO6zTSlSawqprPWwSOE6pYmmX4tD4oYDgtIlFk+s7wYzWQ5ECxrRAwzLyEY5lRkonl bFtg==

Authentication-results: mx.google.com; spf=pass (google.com: domain of owner-auditory@xxxxxxxxxxxxxxx designates 132.206.27.103 as permitted sender) smtp.mailfrom=owner-auditory@xxxxxxxxxxxxxxx

Comments: To: Tamar Regev <tamaregev@xxxxxxxxx>

Delivered-to: dan.ellis@xxxxxxxxx

In-reply-to: <CAG9BnJNgZcxLbOyG1jWkS=JfpX=qaBM6Ns86dyjFKxyVQysU_g@mail.gmail.com>

List-archive: <https://lists.mcgill.ca/scripts/wa.exe?LIST=AUDITORY>

List-help: <https://lists.mcgill.ca/scripts/wa.exe?LIST=AUDITORY>, <mailto:LISTSERV@LISTS.MCGILL.CA?body=INFO%20AUDITORY>

List-owner: <mailto:AUDITORY-request@LISTS.MCGILL.CA>

List-subscribe: <mailto:AUDITORY-subscribe-request@LISTS.MCGILL.CA>

List-unsubscribe: <mailto:AUDITORY-unsubscribe-request@LISTS.MCGILL.CA>

References: <CAG9BnJNgZcxLbOyG1jWkS=JfpX=qaBM6Ns86dyjFKxyVQysU_g@mail.gmail.com>

Reply-to: Boyang Qin <boyangqi@xxxxxxxxxxx>

Sender: AUDITORY - Research in Auditory Perception <AUDITORY@xxxxxxxxxxxxxxx>

Hi Tamer,

I have done something similar using VAD (voiceActivityDetector) in Matlab. I tried to figure out the beginning of the recording. I ended up using Python later instead with webrtcvad (https://github.com/wiseman/py-webrtcvad), as the library in Python is free.

Best,

Boyang

On Fri, Mar 5, 2021 at 12:25 AM Tamar Regev <tamaregev@xxxxxxxxx> wrote:

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