Re: [AUDITORY] Track separation algorithm (King Britt )


Subject: Re: [AUDITORY] Track separation algorithm
From:    King Britt  <0000031420ed93d0-dmarc-request@xxxxxxxx>
Date:    Fri, 28 Jun 2024 23:53:28 -0700

--Apple-Mail-146CD813-A1E5-4409-B64B-71659D1E57AB Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable My favorite is Split Wizard =E2=80=A6MaxforLive plug in.=20 Incredible integration and various models to choose from. Creates a folder for you and also drag and drop right there in Ableton. Has been a favorite for a while. Enjoy and good luck. Gracefully, King Britt Full Teaching Professor | Music=20 University of California=20 San Diego=20 https://linktr.ee/KingBritt sent from my phone office > On Jun 28, 2024, at 9:36=E2=80=AFPM, Dennis Hamm <dennis@xxxxxxxx> w= rote: >=20 > =EF=BB=BFMusic.ai offers that service. Use the =E2=80=9CCinematic stems=E2= =80=9D in your workflow which separates into Dialogue and Music stems. Then r= oute the music stem to "Musical stems=E2=80=9D to separate vocals, guitars, b= ass, strings, keys, drums, etc.. >=20 > https://urldefense.com/v3/__https://music.ai/__;!!Mih3wA!ChYLSsVq1XlGVkRr3= 7jIOlv_qhxp7t_NrJobrCEgG-iRYwZgCrkyq76P7Ztuku7H1Dfbu9X13Lrn5oaM$ >=20 > - Dennis Hamm > dennis@xxxxxxxx >=20 >> On Jun 28, 2024, at 9:08=E2=80=AFPM, Jeremie Ginzburg <jeremie.ginzburg@xxxxxxxx= cgill.ca> wrote: >>=20 >> =EF=BB=BFDear Auditory-listers, >>=20 >> We are trying to find a way to separate speech and music (and other track= s if possible) from a movie audio track. >>=20 >> We are not aware of the latest advances in that specific area. Is anyone a= ware of (maybe AI-based) tools to do that? And if so, what is your opinion o= n its reliability? >>=20 >> Thank you and have a nice weekend :) >>=20 >> -- >> J=C3=A9r=C3=A9mie Ginzburg >> Post-doctoral Researcher - McGill University --Apple-Mail-146CD813-A1E5-4409-B64B-71659D1E57AB Content-Type: text/html; charset=utf-8 Content-Transfer-Encoding: quoted-printable <html><head><meta http-equiv=3D"content-type" content=3D"text/html; charset=3D= utf-8"></head><body dir=3D"auto">My favorite is Split Wizard =E2=80=A6Maxfor= Live plug in.&nbsp;<div>Incredible integration and various models to choose f= rom.</div><div>Creates a folder for you and also drag and drop right there i= n Ableton.</div><div>Has been a favorite for a while.</div><div><br></div><d= iv>Enjoy and good luck.</div><div><br></div><div><br id=3D"lineBreakAtBeginn= ingOfSignature"><div dir=3D"ltr"><div>Gracefully,</div><div><br></div>King B= ritt<div>Full Teaching Professor | Music&nbsp;</div><div><br></div><div>Univ= ersity of California&nbsp;</div><div>San Diego&nbsp;</div><div><br></div><di= v><font color=3D"#000000" style=3D"caret-color: rgb(0, 0, 0); background-col= or: rgba(255, 255, 255, 0);"><a href=3D"https://linktr.ee/KingBritt" style=3D= "caret-color: rgb(0, 0, 0); background-color: rgba(255, 255, 255, 0);">https= ://linktr.ee/KingBritt</a></font></div><div><br></div><div><i>sent from my p= hone office</i></div><div><br></div><div><br></div><div><br></div></div><div= dir=3D"ltr"><br><blockquote type=3D"cite">On Jun 28, 2024, at 9:36=E2=80=AF= PM, Dennis Hamm &lt;dennis@xxxxxxxx&gt; wrote:<br><br></blockquote></d= iv><blockquote type=3D"cite"><div dir=3D"ltr">=EF=BB=BF<span>Music.ai offers= that service. Use the =E2=80=9CCinematic stems=E2=80=9D in your workflow wh= ich separates into Dialogue and Music stems. Then route the music stem to "M= usical stems=E2=80=9D to separate vocals, guitars, bass, strings, keys, drum= s, etc..</span><br><span></span><br><span>https://urldefense.com/v3/__https:= //music.ai/__;!!Mih3wA!ChYLSsVq1XlGVkRr37jIOlv_qhxp7t_NrJobrCEgG-iRYwZgCrkyq= 76P7Ztuku7H1Dfbu9X13Lrn5oaM$ </span><br><span></span><br><span>- Dennis Hamm= </span><br><span>dennis@xxxxxxxx</span><br><span></span><br><blockquo= te type=3D"cite"><span>On Jun 28, 2024, at 9:08=E2=80=AFPM, Jeremie Ginzburg= &lt;jeremie.ginzburg@xxxxxxxx&gt; wrote:</span><br></blockquote><blockquot= e type=3D"cite"><span></span><br></blockquote><blockquote type=3D"cite"><spa= n>=EF=BB=BFDear Auditory-listers,</span><br></blockquote><blockquote type=3D= "cite"><span></span><br></blockquote><blockquote type=3D"cite"><span>We are t= rying to find a way to separate speech and music (and other tracks if possib= le) from a movie audio track.</span><br></blockquote><blockquote type=3D"cit= e"><span></span><br></blockquote><blockquote type=3D"cite"><span> We are not= aware of the latest advances in that specific area. Is anyone aware of (may= be AI-based) tools to do that? And if so, what is your opinion on its reliab= ility?</span><br></blockquote><blockquote type=3D"cite"><span></span><br></b= lockquote><blockquote type=3D"cite"><span>Thank you and have a nice weekend := )</span><br></blockquote><blockquote type=3D"cite"><span></span><br></blockq= uote><blockquote type=3D"cite"><span>-- </span><br></blockquote><blockquote t= ype=3D"cite"><span>J=C3=A9r=C3=A9mie Ginzburg</span><br></blockquote><blockq= uote type=3D"cite"><span>Post-doctoral Researcher - McGill University</span>= <br></blockquote></div></blockquote></div></body></html>= --Apple-Mail-146CD813-A1E5-4409-B64B-71659D1E57AB--


This message came from the mail archive
postings/2024/
maintained by:
DAn Ellis <dpwe@ee.columbia.edu>
Electrical Engineering Dept., Columbia University