search for: kadinger

...http://www.surfnonstop.com/~bandit/speex/1.2beta1_AEC_garble/ The original recordings are in mic.raw and spk.raw. Jean-Marc Valin wrote: > You may have triggered an instability problem. Can you upload your files > somewhere so I can have a look at them? > > Jean-Marc > > Andras Kadinger a ?crit : > >> Greetings everyone, >> >> I was about to compare AEC performance between 1.1.12 and 1.2beta1 when >> I noticed something. >> >> If I configure (and compile) speex-1.1.12 with >> >> ./configure --enable-shared=no --enable-static=ye...

...nd 32767, later slow down but still full-scale, even later the sample values asymptotically approach zero from above; then suddenly the cycle begins again. (I can provide samples of input and output on request.) Is anyone else seeing anything like this? Thanks in advance. Best Regards, Andras Kadinger

Hi Andras, others, Andras Kadinger <bandit <at> surfnonstop.com> writes: > > > Daniel, > I recommend you to start from a simple case and gradually progress > towards your goal. > Can you make things work with the "Speex in a Disco" (Example 6) > testcase at http://ns.s...

...your Subject line so it is more specific > than "Re: Contents of Speex-dev digest..." > > > Today's Topics: > > 1. Re: Speex port to Coldfire or Equivalent (Jean-Marc Valin) > 2. Re: speex in C# please help (Jean-Marc Valin) > 3. Re: Speex Options (Andras Kadinger) > 4. Re: Speex Options (Jean-Marc Valin) > > > ---------------------------------------------------------------------- > > Message: 1 > Date: Fri, 09 Feb 2007 23:34:07 +1100 > From: Jean-Marc Valin <jean-marc.valin@usherbrooke.ca> > Subject: Re: [Speex-dev] Speex...

You may have triggered an instability problem. Can you upload your files somewhere so I can have a look at them? Jean-Marc Andras Kadinger a ?crit : > Greetings everyone, > > I was about to compare AEC performance between 1.1.12 and 1.2beta1 when > I noticed something. > > If I configure (and compile) speex-1.1.12 with > > ./configure --enable-shared=no --enable-static=yes > > it compiles and works as...

The echo suppression in SVN is shaping up quite nicely! I have also observed some - occasional, apparently data-dependent - misbehaviour in AGC. http://www.surfnonstop.com/~bandit/speex/echocard1/

Andras Kadinger wrote: > I have now found a testcase where SVN AGC starts out good, but then it > keeps increasing the gain but never decreasing it, and eventually goes > out through the roof, during the same single recording. I've been doing massive changes in the svn preprocessor, so I'm not to...

Perhaps you could add a warm-start to the AEC, such that the parameters start near the correct values on all but the first use? Stuart On 05/25/2011 08:22 AM, Andras Kadinger wrote: > 2011.05.25. 4:52 keltez?ssel, Arun Raghavan ?rta: >> On Tue, 2011-05-24 at 11:09 -0400, Jean-Marc Valin wrote: >>> The fact that the AEC takes a few seconds to converge is normal. The >> Do you think there might be a way to reduce this? > The shorter you make the...

..., i merely use speex as storage methods. All I ask for is to get the samples as close to original recording as possible after encoding and decoding. Blending, cross fading, pitch adjustment, these signal processing issues are not a concern at this stage. On Oct 31, 2006, at 3:40 PM, Andras Kadinger wrote: > [At the risk of educating you about something you might already know] > > Natural speech in most human languages gradually changes from one > phoneme to the next. > > Concatenating phonemes together from a fixed, prerecorded, > unflexible set would give rise to ab...

On Tue, 2011-06-21 at 20:18 +0200, Kadinger Andr?s wrote: > 2011.06.21. 19:22 keltez?ssel, Arun Raghavan ?rta: > > Hi Andras, others, > > > > Andras Kadinger<bandit<at> surfnonstop.com> writes: > >> > >> Daniel, > >> I recommend you to start from a simple case and gradua...

Jean-Marc Valin ?rta: > Andras Kadinger wrote: >> I have now found a testcase where SVN AGC starts out good, but then it >> keeps increasing the gain but never decreasing it, and eventually goes >> out through the roof, during the same single recording. > > I've been doing massive changes in the svn preproces...

2011.06.21. 19:22 keltez?ssel, Arun Raghavan ?rta: > Hi Andras, others, > > Andras Kadinger<bandit<at> surfnonstop.com> writes: >> >> Daniel, >> I recommend you to start from a simple case and gradually progress >> towards your goal. >> Can you make things work with the "Speex in a Disco" (Example 6) >> t...

2011.06.21. 22:57 keltez?ssel, Arun Raghavan ?rta: > On Tue, 2011-06-21 at 11:39 -0700, Arun Raghavan wrote: > [...] >> I'm also running this on x86 (x86_64, technically), and it's all >> floating-point, so I guess this is a regression somewhere. Will try to >> see if I can run it without any optimisations if possible, which I >> assume should serve as an

On Tue, 2011-05-24 at 11:09 -0400, Jean-Marc Valin wrote: > The fact that the AEC takes a few seconds to converge is normal. The Do you think there might be a way to reduce this? > fact that it needs to completely re-converge in the middle of a call > probably indicates that something went "wrong" in the audio > capture/playback. For example, that could be an

When you say inverted, do you mean a) input and output exchanged with each other, or b) input or output having changed sign numerically (e.g. multiplied by -1)? Andras Jean-Marc Valin wrote: > Make sure that: > > 1) You're using svn head, which has many improvements > 2) The AEC inputs aren't inverted > 3) The delay between the near end and far end signals isn't too

Ok, let me first explain why 5ms matters, even they are 0's, in my particular application. I am working on a speech synthesis system. The basic idea is concatenating pre-recorded phonemes or words into longer sentences. So any missing or extra samples, even it is as short as 5~10ms, cause very noticeable discontinuities. I want to use speex to compress/decompress those pre-recorded

2011.05.25. 4:52 keltez?ssel, Arun Raghavan ?rta: > On Tue, 2011-05-24 at 11:09 -0400, Jean-Marc Valin wrote: >> The fact that the AEC takes a few seconds to converge is normal. The > Do you think there might be a way to reduce this? The shorter you make the tail length the faster it will adapt. But this will make it more important to reduce HW/SW latency so that you don't waste

2011.08.23. 15:38 keltez?ssel, Yanick Bourbeau ?rta: > Since I don't have access to different channels as I record a phone call > using a man in the middle approach, there is something else I can use > to equalize the sound ? What I would do then probably is try to manually separate the two channels/talkers; say channel 1 goes from 0 seconds to 13 seconds, channel 2 goes from 13

[At the risk of educating you about something you might already know] Natural speech in most human languages gradually changes from one phoneme to the next. Concatenating phonemes together from a fixed, prerecorded, unflexible set would give rise to abrupt changes between them (both in phoneme quality and in pitch), and thus make the resulting speech hard to understand and/or uncomfortable