https://community.intel.com/t5/Intel-Integrated-Performance/ippsUpdateNoisePSDMCRA-32s-I-implementation-differences/m-p/906502#M13563 <P>When I try the "Ephraim-Malah Noise Suppressor" example (speech-recAudio-ProcessingNR_exmp) with IPP 5.0 or 5.1, I get different results on different processors.</P> <P>After hours of debugging I found the some implementations of the ippsUpdateNoisePSDMCRA_32s_I routine don't work correctly.</P> <P>When I try the generic (px) and Pentium III (a6) versions of this routine, the noise cancelled audio contains drops in amplitude, which is disturbing and distracting.</P> <P>When I use the SSE2 (w7) and SSE3 (t7) versions, this issue doesn't occur and the result is much better.</P> <P>Is this a known issue? </P> <P>I need at least a generic version of the routine that behaves like the SSE2 or SSE3 version.</P> <P>Thanks for any help!</P> Wed, 11 Oct 2006 07:39:50 GMT adrennan 2006-10-11T07:39:50Z https://community.intel.com/t5/Intel-Integrated-Performance/ippsUpdateNoisePSDMCRA-32s-I-implementation-differences/m-p/906502#M13563 <P>When I try the "Ephraim-Malah Noise Suppressor" example (speech-recAudio-ProcessingNR_exmp) with IPP 5.0 or 5.1, I get different results on different processors.</P> <P>After hours of debugging I found the some implementations of the ippsUpdateNoisePSDMCRA_32s_I routine don't work correctly.</P> <P>When I try the generic (px) and Pentium III (a6) versions of this routine, the noise cancelled audio contains drops in amplitude, which is disturbing and distracting.</P> <P>When I use the SSE2 (w7) and SSE3 (t7) versions, this issue doesn't occur and the result is much better.</P> <P>Is this a known issue? </P> <P>I need at least a generic version of the routine that behaves like the SSE2 or SSE3 version.</P> <P>Thanks for any help!</P> Wed, 11 Oct 2006 07:39:50 GMT https://community.intel.com/t5/Intel-Integrated-Performance/ippsUpdateNoisePSDMCRA-32s-I-implementation-differences/m-p/906502#M13563 adrennan 2006-10-11T07:39:50Z https://community.intel.com/t5/Intel-Integrated-Performance/ippsUpdateNoisePSDMCRA-32s-I-implementation-differences/m-p/906503#M13564 <P>Hello, it might be a bug in Pentium III optimized code in this function. Please report about that issue on <A href="http://premier.intel.com">Intel Premier Support</A></P> <P>Regards,<BR /> Vladimir</P> Thu, 12 Oct 2006 21:35:06 GMT https://community.intel.com/t5/Intel-Integrated-Performance/ippsUpdateNoisePSDMCRA-32s-I-implementation-differences/m-p/906503#M13564 Vladimir_Dudnik 2006-10-12T21:35:06Z