Forums

speech recognition

Started by RichD January 19, 2012
http://www.sfgate.com/cgi-bin/article.cgi?f=/c/a/2012/01/16/BU8C1MOO20.DTL


He claims he can filter speech from background noise.

I recall discussing this possibility years ago.  Someone said, these
filters already exist.  They do - they're notch filters!  It's close
to brain dead, believing that constitutes 'voice filtering'.

Dr. Watts has been working on this for years, so I was wondering
what techniques he's using, how much is public domain.  Anyone
here know anything about the subject, or this  product?
Is it neural nets, DSP filters, or what?


--
Rich
RichD wrote:
> http://www.sfgate.com/cgi-bin/article.cgi?f=/c/a/2012/01/16/BU8C1MOO20.DTL > > > He claims he can filter speech from background noise. > > I recall discussing this possibility years ago. Someone said, these > filters already exist. They do - they're notch filters! It's close > to brain dead, believing that constitutes 'voice filtering'.
If notch filter, why requirement for second microphone ;)
> > Dr. Watts has been working on this for years, so I was wondering > what techniques he's using, how much is public domain. Anyone > here know anything about the subject, or this product? > Is it neural nets, DSP filters, or what? > > > -- > Rich
On Jan 18, 11:51&#2013266080;pm, RichD <r_delaney2...@yahoo.com> wrote:
> http://www.sfgate.com/cgi-bin/article.cgi?f=/c/a/2012/01/16/BU8C1MOO2... > > He claims he can filter speech from background noise. > > I recall discussing this possibility years ago. &#2013266080;Someone said, these > filters already exist. &#2013266080;They do - they're notch filters! &#2013266080;It's close > to brain dead, believing that constitutes 'voice filtering'. > > Dr. Watts has been working on this for years, so I was wondering > what techniques he's using, how much is public domain. &#2013266080;Anyone > here know anything about the subject, or this &#2013266080;product? > Is it neural nets, DSP filters, or what?
[...] There was an article: "Advanced Noise Reduction for Mobile Telephony" in IEEE Computer in 2008 by Lloyd Watts. It's also at < http://www.lloydwatts.com/ > under "Publications"; maybe my browser has a problem, as I can't download the 2008 paper as a PDF file ... Audience Inc. (which makes the chips) mentions a proprietary &#2013266067;Fast Cochlea Transform&#2013266073;&#2013266068; (TM) here: < http://www.audience.com/technology/fast-cochlea.php > At&T sells cell-phones with Audience chipsets. I don't have any personal experience with these kinds of advanced phones. David Bernier
On Jan 19, 11:17&#2013266080;pm, David Bernier <david53...@gmail.com> wrote:
> On Jan 18, 11:51&#2013266080;pm, RichD <r_delaney2...@yahoo.com> wrote:>http://www.sfgate.com/cgi-bin/article.cgi?f=/c/a/2012/01/16/BU8C1MOO2... > > > He claims he can filter speech from background noise. > > > I recall discussing this possibility years ago. &#2013266080;Someone said, these > > filters already exist. &#2013266080;They do - they're notch filters! &#2013266080;It's close > > to brain dead, believing that constitutes 'voice filtering'. > > > Dr. Watts has been working on this for years, so I was wondering > > what techniques he's using, how much is public domain. &#2013266080;Anyone > > here know anything about the subject, or this &#2013266080;product? > > Is it neural nets, DSP filters, or what? > > [...] > > There was an article: > "Advanced Noise Reduction for Mobile Telephony" > in IEEE Computer in 2008 by Lloyd Watts. > It's also at > <http://www.lloydwatts.com/> > under "Publications"; maybe my browser has a > problem, as I can't download the 2008 paper > as a PDF file ... > > Audience Inc. (which makes the chips) mentions > a proprietary &#2013266067;Fast Cochlea Transform&#2013266073;&#2013266068; (TM) > here: > <http://www.audience.com/technology/fast-cochlea.php> > > At&T sells cell-phones with Audience chipsets. > I don't have any personal experience with > these kinds of advanced phones. > > David Bernier
I had a 5 minute conversation with the Credit Card initiation bot. Bottom up noise reduction is mathematics/electronics. Top Down speech matching is AI. Generating likely responses for the domain of the discussion topic. The theory behind the former is 99% worked out, the theory behind the latter is 1% worked out! Herc
On Thu, 19 Jan 2012 06:28:12 -0600, Richard Owlett <rowlett@pcnetinc.com>
wrote:

>RichD wrote: >> http://www.sfgate.com/cgi-bin/article.cgi?f=/c/a/2012/01/16/BU8C1MOO20.DTL >> >> >> He claims he can filter speech from background noise. >> >> I recall discussing this possibility years ago. Someone said, these >> filters already exist. They do - they're notch filters! It's close >> to brain dead, believing that constitutes 'voice filtering'. > >If notch filter, why requirement for second microphone ;) > >
Probably not a filter, but the second mike could be helpful in establishing a baseline for what is 'noise' compared to what my be originating from a point source. Should be some "voice pattern" smarts capable of deciding what data IS from a human source and segregating it from the rest.
>> >> Dr. Watts has been working on this for years, so I was wondering >> what techniques he's using, how much is public domain. Anyone >> here know anything about the subject, or this product? >> Is it neural nets, DSP filters, or what? >> >> >> -- >> Rich
Goddamned overtly cross posting twit.
RichD wrote:
> > http://www.sfgate.com/cgi-bin/article.cgi?f=/c/a/2012/01/16/BU8C1MOO20.DTL > > He claims he can filter speech from background noise. > > I recall discussing this possibility years ago. Someone said, these > filters already exist. They do - they're notch filters! It's close > to brain dead, believing that constitutes 'voice filtering'. > > Dr. Watts has been working on this for years, so I was wondering > what techniques he's using, how much is public domain. Anyone > here know anything about the subject, or this product? > Is it neural nets, DSP filters, or what? > > -- > Rich
A friend of mine, Professor Dana Anderson of the University of Colorado, Boulder, made a statistics-based digital filter that could separate different kinds of music mixed together, as well as music from noise. The demo was really striking--you mix together, say jazz and classical music from two MP3 players, feed it through the gizmo, and after (iirc) about 10 seconds of learning, classical comes out of one speaker and jazz out of the other. Magic stuff--published in IEEE Acoustics around 2006, I think. Cheers Phil Hobbs -- Dr Philip C D Hobbs Principal Consultant ElectroOptical Innovations LLC Optics, Electro-optics, Photonics, Analog Electronics 160 North State Road #203 Briarcliff Manor NY 10510 845-480-2058 hobbs at electrooptical dot net http://electrooptical.net
Phil Hobbs <pcdhSpamMeSenseless@electrooptical.net> writes:

> A friend of mine, Professor Dana Anderson of the University of Colorado, > Boulder, made a statistics-based digital filter that could separate > different kinds of music mixed together, as well as music from noise. > The demo was really striking--you mix together, say jazz and classical > music from two MP3 players, feed it through the gizmo, and after (iirc) > about 10 seconds of learning, classical comes out of one speaker and > jazz out of the other. Magic stuff--published in IEEE Acoustics around > 2006, I think.
That sounds really impressive, if it works as well as you describe. -- Jesse F. Hughes "Mathematicians who read proofs of my results seem to basically lose some part of themselves, like it rips at their souls, and they are no longer quite right in the head." -- James S. Harris, Geek Cthulhu
On Thu, 19 Jan 2012 06:28:12 -0600, Richard Owlett
<rowlett@pcnetinc.com> wrote:

>RichD wrote: >> http://www.sfgate.com/cgi-bin/article.cgi?f=/c/a/2012/01/16/BU8C1MOO20.DTL >> >> >> He claims he can filter speech from background noise. >> >> I recall discussing this possibility years ago. Someone said, these >> filters already exist. They do - they're notch filters! It's close >> to brain dead, believing that constitutes 'voice filtering'. > >If notch filter, why requirement for second microphone ;)
Looks like maybe a combination of adaptive noise cancelling and maybe a little bit of beamforming. Definitely not a notch filter.
>> Dr. Watts has been working on this for years, so I was wondering >> what techniques he's using, how much is public domain. Anyone >> here know anything about the subject, or this product? >> Is it neural nets, DSP filters, or what? >> >> >> -- >> Rich
Eric Jacobsen Anchor Hill Communications www.anchorhill.com
On 1/19/2012 8:35 AM, Phil Hobbs wrote:
> RichD wrote: >> >> http://www.sfgate.com/cgi-bin/article.cgi?f=/c/a/2012/01/16/BU8C1MOO20.DTL >> >> He claims he can filter speech from background noise. >> >> I recall discussing this possibility years ago. Someone said, these >> filters already exist. They do - they're notch filters! It's close >> to brain dead, believing that constitutes 'voice filtering'. >> >> Dr. Watts has been working on this for years, so I was wondering >> what techniques he's using, how much is public domain. Anyone >> here know anything about the subject, or this product? >> Is it neural nets, DSP filters, or what? >> >> -- >> Rich > > A friend of mine, Professor Dana Anderson of the University of Colorado, > Boulder, made a statistics-based digital filter that could separate > different kinds of music mixed together, as well as music from noise. > The demo was really striking--you mix together, say jazz and classical > music from two MP3 players, feed it through the gizmo, and after (iirc) > about 10 seconds of learning, classical comes out of one speaker and > jazz out of the other. Magic stuff--published in IEEE Acoustics around > 2006, I think. > > Cheers > > Phil Hobbs
Not exactly the same, but in a similar vein I have experimented with the following software: http://www.celemony.com/cms/ It allows you to take say, a single track audio file of a complex strummed guitar chord, separate out the chord into its constituent notes, manipulate the frequencies of the constituent notes, and then reassemble the whole thing back into a single audio file.
"Jesse F. Hughes" <jesse@phiwumbda.org> wrote:
> Phil Hobbs <pcdhSpamMeSenseless@electrooptical.net> writes: > > > A friend of mine, Professor Dana Anderson of the University of > > Colorado, Boulder, made a statistics-based digital filter that could > > separate different kinds of music mixed together, as well as music from > > noise. The demo was really striking--you mix together, say jazz and > > classical music from two MP3 players, feed it through the gizmo, and > > after (iirc) about 10 seconds of learning, classical comes out of one > > speaker and jazz out of the other. Magic stuff--published in IEEE > > Acoustics around 2006, I think. > > That sounds really impressive, if it works as well as you describe.
Here's a great little web demo of ICA - Independent Component Analyses. It can separate sources mixed together when recorded in different "microphones" (I assume the demo is just a mathematical mixing and not done by recording). http://research.ics.tkk.fi/ica/cocktail/cocktail_en.cgi This approach makes the assumption that the source signals are linearly mixed together at different levels in each microphone recording (due to the different distances each source is away from the microphone) but can separate as many different sources as you have microphones. More info: http://en.wikipedia.org/wiki/Independent_component_analysis I would guess the telephone technology is using something similar since they added a second microphone. The only statistical requirement for this to work is that the sources must have a non-Gaussian distribution. BTW, this stuff is WAY past "notch filters" in complexity and power and performance. -- Curt Welch http://CurtWelch.Com/ curt@kcwc.com http://NewsReader.Com/