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 anywhere I can find more information on how to use this function? Thanks for your help, Steve _________________________________________________________________ Express yourself instantly with MSN Messenger! Download today it's FREE! http://messenger.msn.click-url.com/go/onm00200471ave/direct/01/
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 performing my experiments. Complexity is being actively used in the following functions in the libspeex library for Win32: File: cb_search.c split_cb_search_shape_sign -----vq_nbest_sign -----vq_nbest File: ltp.c Function: pitch_search_3tap -----open_loop_nbest_pitch 1) What is "Complexity" used for? What is its role in the codebook search algorithm besides allocating the stack sizes? 2) How does "Complexity" effect the search through the codebook to encode the residual coming out of the short-term predictor? 3) How does "Complexity" effect the calculation of pitch and pitch gains for a 3 tap filter for the long-term predictor? 4) Can I manipulate "Complexity" in some fashion so that I can keep the quality of the voice constant while varying the bit-rate by changing the "Quality" parameter? 5) What changes do I have to make in the existing libspeex.lib files in order to have a "Complexity" greater than 10? Thanks a lot for helping me out. I am having a bit of difficulty in understanding the underlying logic within the functions mentioned above. Sincerely, Aninda
> 1) What is "Complexity" used for? What is its role in the codebook search > algorithm besides allocating the stack sizes?The higher the complexity, the better the codebook search and the the pitch search. Basically, for both pitch and codebook, the complexity value is the number of hypothesis I keep at the same time. The higher the complexity value, the higher the quality, although it doesn't make much difference above 3. Many people won't even notice it at all, except in some special cases (e.g. encoding DTMF at 8 kbps)> 2) How does "Complexity" effect the search through the codebook to encode > the residual coming out of the short-term predictor?see 1)> 3) How does "Complexity" effect the calculation of pitch and pitch gains for > a 3 tap filter for the long-term predictor?see 1)> 4) Can I manipulate "Complexity" in some fashion so that I can keep the > quality of the voice constant while varying the bit-rate by changing the > "Quality" parameter?You can manipulate it in any way you like, but I doubt it will be worth the trouble (compared to just using the highest setting you can afford).> 5) What changes do I have to make in the existing libspeex.lib files in > order to have a "Complexity" greater than 10?Just increase the stack size and remove the checks for complexity>10. Note however that you're very unlikely to see any difference. Jean-Marc -- Jean-Marc Valin <Jean-Marc.Valin@USherbrooke.ca> Universit? de Sherbrooke