similar to: Speex support for TI DaVinci processor

Jerry, Thanks for the response; basically, I need to get just the narrow band working now (maybe use advanced features such as jitter buffer, echo cancellation, VAD, etc in the future); the DSP will do the encode and decode simultaneously as data are available. My main objective is just do a voice application that runs on the ARM side of the DaVinci with the codec running on the DSP side; the

Andy Ngo wrote: > Thanks Jean-Marc. Is there a Speex trunk for the C64xx I can use? Or > do I have to figure what options > to turn on (in configure) when building the library? Thanks. Support is in the main version. Just look at the TI/ directory for extra TI-related stuff. Jean-Marc > Regards, > Andy Ngo > > ----- Original Message ---- > From: Jean-Marc Valin

Hi, My company just recently bought a TI DaVinci development board and I'm trying to port Speex to run on it. The TI DaVinci chip has an ARM926 processor and a TMS320C64+ DSP in it. I was able to get Speex somewhat working on a TMS320VC5510 about a year ago but I was wondering is there anything special I need to do to get Speex working on the TMS320C64+ DSP in the DaVinci chip. I

Hi, My company just recently bought a TI DaVinci development board and I'm trying to port Speex to run on it. The TI DaVinci chip has an ARM926 processor and a TMS320C64+ DSP in it. I was able to get Speex somewhat working on a TMS320VC5510 about a year ago but I was wondering is there anything special I need to do to get Speex working on the TMS320C64+ DSP in the DaVinci chip. I

I am in the process of dropping the TI DSP lib fft routines into the AEC. Currently, FFTWrap.c uses the USE_SMALLFT and USE_KISS_FFT to select between two packages of FFT routines. ] #ifdef USE_SMALLFT ... #elif defined(USE_KISS_FFT) ... #else #error No other FFT implemented #endif My guess is that every DSP and many other processors will have their own specific FFT and iFFT. What method

Do you need to encode and/or decode? I did some work optimizing the DM642 speex 1.1.11.1 encoder earlier this year. I was able to reduce the narrow band MIPS from approx 30 to 16 using some of the #pragmas and optimizing the functions (Following the BlackFin example.) The project I was working on has been put on hold so I haven't looked at the more recent changes. If you are tight on

Hi Jean-Marc, I have tested Speex in fixed-point mode on my PC without clicking noise. As I mentioned below, I tested Speex in fixed-point mode running natively on the ARM side of the DaVinci without click noise. I only get the clicking noise when running Speex on the DSP side. For the TI C64+ DSP on the DaVinci processor, the TI-specific switches doesn't do much other than defining the

Tried your fixed_generic.h change but that didn't help. Andy ----- Original Message ---- From: Andy Ngo <ndno72-speex@yahoo.com> To: Jean-Marc Valin <jean-marc.valin@usherbrooke.ca> Cc: speex-dev@xiph.org Sent: Wednesday, December 12, 2007 4:13:35 PM Subject: Re: [Speex-dev] 4kbps sounds robotic on TMS320C64 Jean-Marc, Yes, fixed-point is enabled (#define FIXED_POINT in

Hi, I've been trying to get Speex to compile and run on the DSP of TI's new DaVinci System-On-Chip processor, which has both an ARM (ARM926) and a DSP (C64+, based on the C6400). I used the latest code (1.2beta) and followed the example in the speex- 1.2beta1/ti/speex_C64_test trunk to build the Speex library for the DSP. Basically I have a loopback application on the ARM that samples

Hi Jerry, I'd say the best would be to simply replace the #ifdef USE_SMALLFT by #ifdef USE_TI_FFT #include "ti_fft_wrapper.h" #elif defined(USE_SMALLFT) and have everything in the include file. There's no real point in overriding individual functions since they all go together. Also, make sure you wrap the FFT in the same way as I did with the fixed-point kissfft. For example,

Hi, I am attempting to port the speex library to TI Davinci DM35x Family. My questions are: 1. What is the best ./configure option for it? Is it ARM5e / ARM4 ? when I tried these two the during the compiled a warning "I suppose you can have a [ARM4/ARM5E/Blackfin] that has float instructions?" 2. is there any available demos for the echo cancellation because I can get it

Sorry everyone, but I figured it out; it's working now. The problem was in my monoToStereo and stereoToMono functions (the Linux OSS driver on the ARM side only supports stereo so I had to convert it to mono before feeding it to Speex); also I had an alignment issue with my buffers I was using on the DSP side. Thanks Jim/Jean-Marc for your help! Regards, Andy ----- Original Message ----

(Resending since the archive seems to have eaten the text.) I'm working on getting Speex running on a TI Davinci (6441), on both the ARM and the DSP. My immediate goal is to understand the processing requirements on different architectures so that I can properly specific an engineering project. I have it up and running on the ARM, and I just wanted to see if anyone could sanity-check

I'm trying to make a design decision between a TI 6416 or DM642 (fixed point) and 6713 (floating point) platform. The application is a 32 channel speech encoder. (CBR only, 8khz, 8kbps) To get a feel for the computational load, I am running 1 second (50 frames) of voice through the encoder. My profile of the 6416 indicates I'm at 27.4M cycles/channel. I need to get below 720Mhz/32

I started my project using the CodeComposerStudio speex_C64_test.pjt in speex 1.1.11.1. To build using floating point, I created a new project with the same files and modified ti\config.h to #undef FIXED_POINT. Is there a better way to configure a floating point processor? I have a few TI specific optimizations that could go into the next release. What's the procedure for submitting code?

Jean-Marc, Yes, fixed-point is enabled (#define FIXED_POINT in config.h). I haven't tried anything lower than 4kbps; like I mentioned, 6kbps sounds fine so it's very strange. The only code I changed to get 4kbps was setting quality to 1 so that is the only difference in my test code between using 4kbps and 6kbps. It seems to be in the encoder. On the ARM side, I encoded a 8Khz 16-bit

Hi, I'm currently working on the TI DaVinci processor, which has an ARM926 processor and a TMS320C64+ DSP in it. I have been using Speex 6kbps (narrowband, quality=2, complexity=1, perceptual_enh=0) on the DSP C64+ side without any issues; the voice sounds very good for such a low bandwidth requirement. However, recently, I tried out the 4kbps mode (changing quality to 1) on the DSP and it

The majority of a Speex encoder app does fit in a 6713. The 6713 has 8K of L1 and another 256K of memory 64K of which can be configured as L2 cache. (16,32,48, or 64K). One level of TI's website seems to incorrectly indicate only 64K of L2. I turned off MANUAL_ALLOC and have it allocating internal memory using calloc(). I did change the L2 cache to 2 way (32K) and adjusted the heap size to

> > Hello everybody. > > I have the same problem like you. I use ARM microcontroller too. > > Here is the list of all functions called by speex_echo_cancel until goes > > into infinite loop: >... > > else > > { > > do > > { > > kf_work(Fout , f, fstride*p, in_stride, factors,st); // ><---------- > > here this

Jerry, I think that just removing the FIXED_POINT define should be sufficient, though you mind want to turn off MANUAL_ALLOC, because I am not sure if the memory usage is identical for the fixed point build, and the constants in config.h are set for the fixed point build. Are you testing on the simulator, or on an eval board? It does not look like the 6713 has enough memory to hold Speex