Rocksolid Light

Welcome to novaBBS (click a section below)

mail  files  register  newsreader  groups  login

Message-ID:  

19 May, 2024: Line wrapping has been changed to be more consistent with Usenet standards.
 If you find that it is broken please let me know here rocksolid.nodes.help


tech / rec.audio.pro / Re: AI is coming to audio - see Adobe's demo

SubjectAuthor
* Re: AI is coming to audio - see Adobe's demoOrlando Enrique Fiol
`* Re: AI is coming to audio - see Adobe's demoScott Dorsey
 `- Re: AI is coming to audio - see Adobe's demoOrlando Enrique Fiol

1
Re: AI is coming to audio - see Adobe's demo

<MPG.3fd42cf67313f9e7989681@news.eternal-september.org>

  copy mid

https://www.novabbs.com/tech/article-flat.php?id=2270&group=rec.audio.pro#2270

  copy link   Newsgroups: rec.audio.pro
Path: i2pn2.org!i2pn.org!eternal-september.org!feeder3.eternal-september.org!news.eternal-september.org!.POSTED!not-for-mail
From: ofi...@verizon.net (Orlando Enrique Fiol)
Newsgroups: rec.audio.pro
Subject: Re: AI is coming to audio - see Adobe's demo
Date: Fri, 1 Dec 2023 17:49:11 -0500
Organization: Surila
Lines: 10
Message-ID: <MPG.3fd42cf67313f9e7989681@news.eternal-september.org>
References: <MPG.3e0bcd1db0f5e7499896a8@news.eternal-september.org>
Reply-To: ofiol@verizon.net
MIME-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Injection-Info: dont-email.me; posting-host="41d7e0d1a3f5658406e4c78b291d3456";
logging-data="2148370"; mail-complaints-to="abuse@eternal-september.org"; posting-account="U2FsdGVkX18mIn2cgY8GqC8FiJPHuwIH9e1jI/F3MoY="
User-Agent: MicroPlanet-Gravity/3.0.6
Cancel-Lock: sha1:xhvbGq5oy0D7aI6PEPMKVQUQhGY=
 by: Orlando Enrique Fiol - Fri, 1 Dec 2023 22:49 UTC

In article <MPG.3e0bcd1db0f5e7499896a8@news.eternal-september.org>,
>Adobe released a demo (https://podcast.adobe.com/enhance)of an
>AI-based audio enhancement routine for voice. You can try it at the link
>above. I recently recorded a chamber music concert at a local church.
>One of the performers spoke for a minute about a piece they were about
>to play. The recording has quite a bit of reverberation and random
>noises. The result from Adobe is surprisingly good, 'tho my wife
>commented that the process altered the timbre of the narrator's voice,
>but not in a way that someone who didn't know her would notice.
What actually constitutes timbral alteration knowledge?

Re: AI is coming to audio - see Adobe's demo

<uki2ir$9rd$1@panix2.panix.com>

  copy mid

https://www.novabbs.com/tech/article-flat.php?id=2276&group=rec.audio.pro#2276

  copy link   Newsgroups: rec.audio.pro
Path: i2pn2.org!i2pn.org!weretis.net!feeder6.news.weretis.net!panix!.POSTED.panix2.panix.com!panix2.panix.com!not-for-mail
From: klu...@panix.com (Scott Dorsey)
Newsgroups: rec.audio.pro
Subject: Re: AI is coming to audio - see Adobe's demo
Date: 3 Dec 2023 14:15:55 -0000
Organization: Former users of Netcom shell (1989-2000)
Lines: 29
Message-ID: <uki2ir$9rd$1@panix2.panix.com>
References: <MPG.3e0bcd1db0f5e7499896a8@news.eternal-september.org> <MPG.3fd42cf67313f9e7989681@news.eternal-september.org>
Injection-Info: reader2.panix.com; posting-host="panix2.panix.com:166.84.1.2";
logging-data="8329"; mail-complaints-to="abuse@panix.com"
 by: Scott Dorsey - Sun, 3 Dec 2023 14:15 UTC

Orlando Enrique Fiol <ofiol@verizon.net> wrote:
>In article <MPG.3e0bcd1db0f5e7499896a8@news.eternal-september.org>,
>>Adobe released a demo (https://podcast.adobe.com/enhance)of an
>>AI-based audio enhancement routine for voice. You can try it at the link
>>above. I recently recorded a chamber music concert at a local church.
>>One of the performers spoke for a minute about a piece they were about
>>to play. The recording has quite a bit of reverberation and random
>>noises. The result from Adobe is surprisingly good, 'tho my wife
>>commented that the process altered the timbre of the narrator's voice,
>>but not in a way that someone who didn't know her would notice.
>What actually constitutes timbral alteration knowledge?

For voice that's a hard problem because the voice consists of a bunch of
fundamentals, plus partials, plus sidebands. Any chance in pitch to
any of them, or any change in their levels, would cause a timbral
change. Would it be audible? Maybe, depending. I can drop a deep notch
into a vocal track at one frequency, and you wouldn't notice it, and I
can drop it somewhere else and it would be obvious.

Back in the seventies, Stockham took digital notch filters to a Caruso
recording, with the intention of notching out all of the horn resonances
that were part of the recording process. But the end result didn't sound
like Caruso... much of the depth of his voice was gone. Was this because
natural vocal resonances were getting notched out? Or was it because
Caruso's voice wasn't really as complex and thick and people remembered it
as being? Folks have been arguing over that one for decades.
--scott
--
"C'est un Nagra. C'est suisse, et tres, tres precis."

Re: AI is coming to audio - see Adobe's demo

<MPG.3fd6adc0b29d91ca989681@news.eternal-september.org>

  copy mid

https://www.novabbs.com/tech/article-flat.php?id=2277&group=rec.audio.pro#2277

  copy link   Newsgroups: rec.audio.pro
Path: i2pn2.org!i2pn.org!eternal-september.org!feeder3.eternal-september.org!news.eternal-september.org!.POSTED!not-for-mail
From: ofi...@verizon.net (Orlando Enrique Fiol)
Newsgroups: rec.audio.pro
Subject: Re: AI is coming to audio - see Adobe's demo
Date: Sun, 3 Dec 2023 15:23:16 -0500
Organization: Surila
Lines: 28
Message-ID: <MPG.3fd6adc0b29d91ca989681@news.eternal-september.org>
References: <MPG.3e0bcd1db0f5e7499896a8@news.eternal-september.org> <MPG.3fd42cf67313f9e7989681@news.eternal-september.org> <uki2ir$9rd$1@panix2.panix.com>
Reply-To: ofiol@verizon.net
MIME-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Injection-Info: dont-email.me; posting-host="f1f85e471802daa1027081773f1cb832";
logging-data="2898044"; mail-complaints-to="abuse@eternal-september.org"; posting-account="U2FsdGVkX1/AqV40ZwgtPkIdt5pa1j/Ep3wvm2PFRrM="
User-Agent: MicroPlanet-Gravity/3.0.6
Cancel-Lock: sha1:Cy8BKp8lSUcrZmCzFv1ZmZw8IIw=
 by: Orlando Enrique Fiol - Sun, 3 Dec 2023 20:23 UTC

In article <uki2ir$9rd$1@panix2.panix.com>, kludge@panix.com writes:
>For voice that's a hard problem because the voice consists of a bunch of
>fundamentals, plus partials, plus sidebands. Any chance in pitch to
>any of them, or any change in their levels, would cause a timbral
>change. Would it be audible? Maybe, depending.

Plus, the vocal timbre would need to be distinguishable from other instrumental
timbres.

>I can drop a deep notch into a vocal track at one frequency, and you wouldn't
notice it, and I
>can drop it somewhere else and it would be obvious.

This only takes vowels into account, whose frequencies could be easily
measured.

>>Back in the seventies, Stockham took digital notch filters to a Caruso
>recording, with the intention of notching out all of the horn resonances
>that were part of the recording process. But the end result didn't sound
>like Caruso... much of the depth of his voice was gone. Was this because
>natural vocal resonances were getting notched out? Or was it because
>Caruso's voice wasn't really as complex and thick and people remembered it
>as being? Folks have been arguing over that one for decades.

Considering how much horn resonances were both highly colored and woefully
incomplete in terms of frequency ranges, Caruso's voice probably sounded little
like his recorded representations. Only live recordings using contemporary
proaudio equipment would settle this question accurately/.


tech / rec.audio.pro / Re: AI is coming to audio - see Adobe's demo

1
server_pubkey.txt

rocksolid light 0.9.81
clearnet tor