similar to: VAD with speex_preprocess()

speex_preprocess() isn't covered in the manual, is it? But, it's very easy to use. If it returns non-zero, voice was detected. Tom "Meir Yeshurun" <mt_yeshurun@hotmail.com> wrote: > > I would like to use speex_preprocess() for voice activity detection. I read > the comments in speex_preprocess.h and the relevant paragraphs in the Speex > manual. Is there

As I understand it, there are two separate ways to get VAD information from Speex: 1) Using the encoder. 2) Using speex_preprocess(). I present the following observations from an application developer's perspective. They may be wrong, in which case I would appreciate corrections. - The two VAD systems are implemented differently. - speex_preprocess()'s VAD provides more accurate

I have a patch for libspeex, which optimises some of the loops in vq_nbest and vq_nbest_sign that speeds up encoding - my results: test file: 10s wav file at 16000 Hz, mono encoding with wideband --quality 3, --comp 3 machine: PIII-900Mhz, 256MB RAM before: 2.78s after: 2.38s I'm still trying to grasp the code (I'm just a coder, no background in sound processing), and just optimised

Dear Jean, Thank you so much for reply my message. I am sorry the function return 38 is speex_bits_write(). This function doesn't work on one of my computers. But after I add the function speex_preprocess(), it works well. I am wondering what is the possible reason? What the function speex_preprocess() does? Another problem I have now is when I enable dtx and vad with function

Hi, I had the same experience. The VAD done in the encoder does not seem to work very well at all. However, the VAD done by speex_preprocess() works much better. You will also get better results if you enable the denoiser, I think. peex_preprocess_ctl(preprocess, SPEEX_PREPROCESS_SET_DENOISE, &denoise_enabled); speex_preprocess_ctl(preprocess, SPEEX_PREPROCESS_SET_VAD,

Dear Jean, > Actually, 38 is normal for the 15 kbps mode. For the rest, could you > give more details. Also, what platform is the problematic machine? (What > CPU, what OS, what compiler). Thanks for your reply. The platform is WindowsXP Professional with SP1. CPU is Celeron CPU 1.70GHz. Compiler is VC++ 6.0. I have enabled VAD and DTX . In this computer, speex_bits_write() still

Hello, first of all, sorry for the joke in the subject ;-) I have successfully update the speex library my software was using from 1.1.12 to 1.2beta1 (1.1.13). It is a VoIP software, where i set preprocessor VAD on and use the result of speex_preprocess() to determine if there is voice activity. I must say that it works fine...since i have update to the new version. Ive been testing, and

Hi all and Jean-Marc, Firstly thanks a lot to you for helps, at last I accomplished to use speex-1.2beta1 in my speech application. I try to understand speex source code and improve speech quality. The problem in my application (like many people in the list says) is noise. So I've added VAD in preprocessor as following. VAD in preprocessor is very good, there is not noise outside speech. I

Hi all! Speex can encode voice in eight different bit-rates that can be invoked by setting the "Quality" parameter. Another parameter that is of importance to what I am trying to achieve is "Complexity". My questions deal with "Complexity". I know that the CPU requirements for complexity 10 is about 5 times higher than for complexity 1. I have verified it while

Hello, in my project im using speex 1.2rc1 and the preprocessor VAD seems to only separate complete silence from not complete silence frames. The Speex Manual, you can read "The voice activity detector (VAD) provided by the preprocessor is more advanced than the one directly provided in the codec." but if you go to the source code in preprocess.c line 995 "/* FIXME: This VAD

Hi all, as in subject, speex_preprocess inject noise in my data. Someone can help ? Here's the way that i'm using: #define NN 160 /* 20msec di audio */ #define AUDIO_SAMPLERATE 8000 spx_int16_t TEMP_Buffer[NN]; speex_pp_state = speex_preprocess_state_init(NN,AUDIO_SAMPLERATE); c = denoise; speex_preprocess_ctl(speex_pp_state, SPEEX_PREPROCESS_SET_DENOISE,&c); c = agc;

Hi all and Jean-Marc, Firstly thanks a lot to you for helps, at last I accomplished to use speex-1.2beta1 in my speech application. I try to understand speex source code and improve speech quality. The problem in my application (like many people in the list says) is noise. So I've added VAD in preprocessor as following: int param_enabled = 1; int param_disabled = 0; int sampling_rate

Jesus, Unfortunately, FFT and magic algorithms don't work (yet?). You might want to try this if you're not satisfied with Speex VAD: http://lists.xiph.org/pipermail/speex-dev/2008-August/006860.html It won't perform any miracles, but I think it works pretty well and is easy to tweak. Tom >---- Original Message ---- >From: jmorion at toomeeting.com >To: speex-dev at

Hi, I am trying to get speex_preprocess in real time for Arm. Tried 32.32 fixed point but looks like even that precision is also not enough. Any suggesions? Regards, Phani. ===== !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! !The butterfly counts not months but moments,! ! and has time enough. ! !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!

Hi, While most of the native functions take float[] array as input, why the function speex_preprocess(...) can only accept short[] array? How do I call this function if I have float[] array inputs? Do I need to convert the floats to Integers back and forth? Thank you in advance. Long Deng -------------- next part -------------- An HTML attachment was scrubbed... URL:

Hi,all I do some work on ARM cpu with VS2005, speex1.2beta. I use the FIXED_POINT define and it works well of codec and decode. but the speex_preprocess() still cannot work real time. I look into the soucecode , and didn't find any fix-point #ifdef computation . So I wish there should be some fix in the future version. If you already done the similar, pls tell me , thanks! Fan

Hi, I'm trying to get speex working on an ARM board (ARM926EJ-Sid(wb) core, ARM 5TE architecture) and getting segfaults if build with "--enable-fixed-point --enable-arm5e-asm" options. If I use just "--enable-fixed-point", then it runs fine, but once I add "--enable-arm5e-asm" it start crashing (I use testenc to test it). Further investigation showed, that it

> -----Message d'origine----- > De : Jean-Marc Valin [mailto:jean-marc.valin at usherbrooke.ca] > Envoy? : dimanche, 14. juin 2009 20:46 > ? : Stephane Lesage > Cc : speex-dev at xiph.org > Objet : Re: [Speex-dev] Resampler saturation > > Just to make sure I understand, the two patches you sent are > two different ways to fix the problem, with the only >

Hi, Here are the next two patches for the data export. speex_get_psd should be applied after speex_get_agc_gain (sent in previous mail). It allows applications to get the power spectrum for the signal and the noise estimate. speex_get_prob should be applied last. It allows fetching the speech probability of the current frame (the value that the _PROB_START and _PROB_CONTINUE parameters are

Jean-Marc Valin wrote: >>Reverberation suppression? >> >> > >Basically, it means that if you are in a room with lots of echo (long >decay), I can reduce it a bit. > > > >>I guess this would help reduce local source echoes? I've never >>_noticed_ that to be a problem in my use, but I would imagine that >>using a notebook's