Support

If you have a problem or need to report a bug please email : support@dsprobotics.com

There are 3 sections to this support area:

DOWNLOADS: access to product manuals, support files and drivers

HELP & INFORMATION: tutorials and example files for learning or finding pre-made modules for your projects

USER FORUMS: meet with other users and exchange ideas, you can also get help and assistance here

NEW REGISTRATIONS - please contact us if you wish to register on the forum

Users are reminded of the forum rules they sign up to which prohibits any activity that violates any laws including posting material covered by copyright

detecting emotions and maybe something else in voice

For general discussion related FlowStone

detecting emotions and maybe something else in voice

Postby tester » Mon Mar 17, 2014 12:37 am

I'm starting to think about a project, that would measure somewhat emotional correlates of continuous speech.

Found this article and this article. While still some articles must be found I guess, few questions emerge. These parameters are pointed:

- fundamental frequency [can be tracked automatically by Martin's pitch tracker]
- speech rate [how to automate it to get decent results? how to approach it?],
- pauses [I guess this is silence detector],
- voice intensity [peak detection or RMS?],
- voice onset time [I'm confused with this one],
- jitter (pitch perturbations) [as I understand, this is calculated over the pitch detection array],
- shimmer (loudness perturbations) [as I understand, this is calculated over the peak/RMS detection array],
- voice breaks [I'm confused with this one],
- pitch jumps [I'm confused with this one, i.e. what to measure],
- and measures of voice quality:
-- the relative extent of high- versus low-frequency energy in the spectrum [what exactly is measured? two filters and RMS per band?],
-- the frequency and bandwidth of energy peaks in the spectrum due to natural resonances of the vocal tract called formants [and how to approach them?].

Should be some other parameters in the game?

It's a starting point I guess. The main goal would be to create some sort of oscilloscope view,s that will show emotional cues that come out of acoustic measurements/features. Yet we need to figure out what is what. :mrgreen:
Need to take a break? I have something right for you.
Feel free to donate. Thank you for your contribution.
tester
 
Posts: 1786
Joined: Wed Jan 18, 2012 10:52 pm
Location: Poland, internet

Re: detecting emotions and maybe something else in voice

Postby MegaHurtz » Mon Mar 17, 2014 11:38 am

I know where you zoned out :)
192k @ 8ms
User avatar
MegaHurtz
 
Posts: 105
Joined: Mon Aug 11, 2008 6:29 pm
Location: Eindhoven/Nederland

Re: detecting emotions and maybe something else in voice

Postby MegaHurtz » Mon Mar 17, 2014 12:55 pm

Think your best bet would be to keep comparing fft's for a couple of years, get some skill at it.
192k @ 8ms
User avatar
MegaHurtz
 
Posts: 105
Joined: Mon Aug 11, 2008 6:29 pm
Location: Eindhoven/Nederland

Re: detecting emotions and maybe something else in voice

Postby tester » Mon Mar 17, 2014 4:31 pm

MH - just stop.
Need to take a break? I have something right for you.
Feel free to donate. Thank you for your contribution.
tester
 
Posts: 1786
Joined: Wed Jan 18, 2012 10:52 pm
Location: Poland, internet

Re: detecting emotions and maybe something else in voice

Postby Xtinct » Tue Mar 18, 2014 2:56 am

tester wrote:MH - just stop.

Yeah just stop maybe he's onto something here,
sorry I meant on somthing I enjoy a good drug fueled fantasy as much as the the next man,
but if the ability to discern emotions from the voice was possible there would be a lot less water boarding, and lie detectors would be alot simpler.
but using the voice as a source of modulation with all its nuances is a great idea :)
Xtinct
 
Posts: 106
Joined: Fri Feb 11, 2011 12:06 am

Re: detecting emotions and maybe something else in voice

Postby MegaHurtz » Tue Mar 18, 2014 12:29 pm

Isnt this good text to speech analysis?

sidenote: general objective ill defined and vague.
sidenote: user reads paragraph.
sidenote: user zoned out. action: hint at actual understanding.
sidenote: user gets angry at the prospect of actual understanding.
sidenote: user blames world.
sidenote: user reverts to 4chan lingo/mentality. action: leave for dead/check netbios.
sidenote: user zoned out.

Maybe I am a robot.. :lol:
192k @ 8ms
User avatar
MegaHurtz
 
Posts: 105
Joined: Mon Aug 11, 2008 6:29 pm
Location: Eindhoven/Nederland

Re: detecting emotions and maybe something else in voice

Postby Jay » Tue Mar 18, 2014 4:02 pm

Lol Megahurtz you crack me up m8 :lol:

Tester here is a place i find really interesting! they have a raft of funky software and resources all to do with speech, speech synthesis and recognition http://www.phon.ucl.ac.uk/resource/

there might be some stuff in there that will help you!

Regards
Jay
 
Posts: 276
Joined: Tue Jul 13, 2010 5:42 pm

Re: detecting emotions and maybe something else in voice

Postby Tzarls » Tue Mar 18, 2014 9:22 pm

Xtinct wrote:
tester wrote:MH - just stop.

... if the ability to discern emotions from the voice was possible there would be a lot less water boarding, and lie detectors would be alot simpler...


Well, a couple of decades ago it was impossible to separate individual notes from, say, a recorded piano chord. Then came Melodyne (and others) and the impossible became possible. It´s just a matter of figuring out how it can be done, and if we have enough CPU power to do it in some practical way.
Tzarls
 
Posts: 54
Joined: Thu Oct 21, 2010 2:10 am

Re: detecting emotions and maybe something else in voice

Postby MegaHurtz » Tue Mar 18, 2014 9:49 pm

Dont warn me like this tester thats just childish.

"MH, you can be sure that I will take proper actions if you are going to do again what you did in the past. Go posting your spam somewhere else."

Tzarls wrote:
Xtinct wrote:
tester wrote:MH - just stop.

... if the ability to discern emotions from the voice was possible there would be a lot less water boarding, and lie detectors would be alot simpler...


Well, a couple of decades ago it was impossible to separate individual notes from, say, a recorded piano chord. Then came Melodyne (and others) and the impossible became possible. It´s just a matter of figuring out how it can be done, and if we have enough CPU power to do it in some practical way.


It has progressed a lot, but tension is not a good basis to prosecute anyone. Offcourse hes tense. Or hes an absolute psychopath. Now who did?. Or in other words.. hes lying lets waterboard him yeehaw!
192k @ 8ms
User avatar
MegaHurtz
 
Posts: 105
Joined: Mon Aug 11, 2008 6:29 pm
Location: Eindhoven/Nederland

Re: detecting emotions and maybe something else in voice

Postby tester » Tue Mar 18, 2014 11:40 pm

Look MH - I sent you a friendly warning on PM and not in public exchange, because this is how it works. I sent you a friendly warning, so that you think twice before act like a stupid kid again. It's not the first time when you are spamming topics. If you are unable to behave in discussion - it's your choice. Just be aware of the consequences.
Need to take a break? I have something right for you.
Feel free to donate. Thank you for your contribution.
tester
 
Posts: 1786
Joined: Wed Jan 18, 2012 10:52 pm
Location: Poland, internet

Next

Return to General

Who is online

Users browsing this forum: No registered users and 84 guests