Re: 60 Hz hum causing problems with speech recognition (Lloyd Watts )

Subject: Re: 60 Hz hum causing problems with speech recognition From: Lloyd Watts <lwatts@xxxxxxxx> Date: Tue, 16 Jun 2009 11:29:47 -0700 List-Archive:<http://lists.mcgill.ca/scripts/wa.exe?LIST=AUDITORY> --_000_A73A509F70C65245B2B010D00825C402070254FA23EXMaudiencelo_ Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable Hello Tarun, I've been using my USBpre since 2001 and have been extremely happy with it. http://www.sounddevices.com/products/usbpremaster.htm Lloyd ________________________________ From: AUDITORY - Research in Auditory Perception [mailto:AUDITORY@xxxxxxxx= ILL.CA] On Behalf Of Tarun Pruthi Sent: Tuesday, June 16, 2009 10:02 AM To: AUDITORY@xxxxxxxx Subject: Re: [AUDITORY] 60 Hz hum causing problems with speech recognition Hi Linda: I am trying to make a speech command recognizer using a standard open-sourc= e speech recognizer on my laptop. Most of the work I do, is either on my of= fice desk or home. I guess the sources of noise would be the usual things: = lights, unclean power, wireless signals etc. Tarun On Tue, Jun 16, 2009 at 11:57 AM, Linda Seltzer <lseltzer@xxxxxxxx= u<mailto:lseltzer@xxxxxxxx>> wrote: What exactly is the experiment you are trying to do or the test that you are conducting and where is the recording being done? > Hi all: > I have been having a lot of problems lately with 60 Hz humming noise in m= y > speech recordings (I will confess that most of my tests have been on > windows/linux laptops - and my guess is that they probably have much wors= e > recording quality than desktops on average - but we live in a mobile worl= d > now and I have to make it work on laptops). Whenever it is there, it > causes > a serious drop in speech recognition accuracy, especially since it comes > in > very randomly at times giving for example clean recordings during speaker > enrollment and noisy recordings in live testing. The problem is even wors= e > on linux which has given me all kinds of artifacts in the recordings > besides > the 60 Hz hum - my guess is that this is most likely because of driver > problems. > > So, I have 3 questions: > 1. What is the source of this 60 Hz noise? Powerline? RF interference? I > have tried disconnecting the power cord - it works sometimes, but not > always. > 2. Is there a standard way to get rid of the 60 Hz hum and ensure clean > recordings for the purposes of speech recognition? The only way I can > think > of is to use notch filters at 60 Hz, and some of the harmonics, say 120 H= z > and 180 Hz, since most of the times it doesn't manifest as a single tone > at > 60 Hz, but has harmonics all over the frequency range. > 3. If this is a well-known problem with sound cards, then why aren't we, > speech recognition community, trying to come up with a mandatory > compliance > standard for sound card manufacterers which ensures that the microphone > input is not corrupted by 60/50 Hz noise? That should provide a big boost > to > speech recognition accuracies, and a wider acceptance of speech > recognition. > > Tarun > Senior Research Engineer > Think A Move, Ltd > --_000_A73A509F70C65245B2B010D00825C402070254FA23EXMaudiencelo_ Content-Type: text/html; charset="us-ascii" Content-Transfer-Encoding: quoted-printable <html xmlns:v=3D"urn:schemas-microsoft-com:vml" xmlns:o=3D"urn:schemas-micr= osoft-com:office:office" xmlns:w=3D"urn:schemas-microsoft-com:office:word" = xmlns=3D"http://www.w3.org/TR/REC-html40"> <head> <META HTTP-EQUIV=3D"Content-Type" CONTENT=3D"text/html; charset=3Dus-ascii"= > <meta name=3DGenerator content=3D"Microsoft Word 11 (filtered medium)">  <style>  </style>  </head> <body lang=3DEN-US link=3Dblue vlink=3Dblue> <div class=3DSection1> Hello Tarun,<o:p></o:p><= /p> <o:p> </o:p> I’ve been using my USBpre since = 2001 and have been extremely happy with it.<o:p></o:p> <a href=3D"http://www.sounddevices.com/products/usbpremaster.htm">http://www.s= ounddevices.com/products/usbpremaster.htm</a><o:p></o:p> <o:p> </o:p> Lloyd<o:p></o:p> <o:p> </o:p> <o:p> </o:p> <div> <div class=3DMsoNormal align=3Dcenter style=3D'text-align:center'> <hr size=3D2 width=3D"100%" align=3Dcenter tabindex=3D-1> </div> From: AUDITORY= - Research in Auditory Perception [mailto:AUDITORY@xxxxxxxx On Behalf Of Tarun Pruthi Sent: Tuesday, June 16, 2009= 10:02 AM To: AUDITORY@xxxxxxxx= Subject: Re: [AUDITORY] 60 H= z hum causing problems with speech recognition<o:p></o:p> </div> <o:p> </o:p> Hi Linda:<o:p></o:p> <div> <o:p> </o:p> </div> <div> I am trying to make a speech command recognizer using a standard open-source speech recognizer on my laptop. Most of the work I do, is eithe= r on my office desk or home. I guess the sources of noise would be the usual thi= ngs: lights, unclean power, wireless signals etc.<o:p></o:p> </div> <div> <o:p> </o:p> </div> <div> Tarun<o:p></o:p><= /span> <div> On Tue, Jun 16, 2009 at 11:57 AM, Linda Seltzer <<a href=3D"mailto:lseltzer@xxxxxxxx">lseltzer@xxxxxxxx</a>= > wrote:<o:p></o:p> What exactly is the experiment you are trying to do or the test tha= t you are conducting and where is the recording being done?<o:p></o:p></fo= nt> <div> <div> > Hi all: > I have been having a lot of problems lately with 60 Hz humming noise i= n my > speech recordings (I will confess that most of my tests have been on<b= r> > windows/linux laptops - and my guess is that they probably have much w= orse > recording quality than desktops on average - but we live in a mobile w= orld > now and I have to make it work on laptops). Whenever it is there, it<b= r> > causes > a serious drop in speech recognition accuracy, especially since it com= es > in > very randomly at times giving for example clean recordings during spea= ker > enrollment and noisy recordings in live testing. The problem is even w= orse > on linux which has given me all kinds of artifacts in the recordings<b= r> > besides > the 60 Hz hum - my guess is that this is most likely because of driver= > problems. > > So, I have 3 questions: > 1. What is the source of this 60 Hz noise? Powerline? RF interference?= I > have tried disconnecting the power cord - it works sometimes, but not<= br> > always. > 2. Is there a standard way to get rid of the 60 Hz hum and ensure clea= n > recordings for the purposes of speech recognition? The only way I can<= br> > think > of is to use notch filters at 60 Hz, and some of the harmonics, say 12= 0 Hz > and 180 Hz, since most of the times it doesn't manifest as a single to= ne > at > 60 Hz, but has harmonics all over the frequency range. > 3. If this is a well-known problem with sound cards, then why aren't w= e, > speech recognition community, trying to come up with a mandatory > compliance > standard for sound card manufacterers which ensures that the microphon= e > input is not corrupted by 60/50 Hz noise? That should provide a big bo= ost > to > speech recognition accuracies, and a wider acceptance of speech > recognition. > > Tarun > Senior Research Engineer > Think A Move, Ltd ><o:p></o:p> </div> </div> </div> <o:p> </o:p> </div> </div> </body> </html> --_000_A73A509F70C65245B2B010D00825C402070254FA23EXMaudiencelo_--

This message came from the mail archive
http://www.auditory.org/postings/2009/
maintained by:

DAn Ellis <dpwe@ee.columbia.edu>
Electrical Engineering Dept., Columbia University