Actually, the Xbox One has complete audio chip(s) for games that can handle 512 simultaneous voices and will capture voice at 24 KHz PCM, and several more for Kinect processing.   We still don't know what some of the extra co-processors do.

As I understand developers can take up to 4 of the CU's of the GPU for sound processing on the PS4.  As we know the PS4 will have in game chat, and this chip seems to be assisting with that as well.

The Xbone audio chip was made to works with the Kinect feature all the time.... of course there are simple games tasks too but if you need to do any raycasting audio you will need to use GPU CUs on Xbone too.

PS4 audio chip do the same except the Kinect part... so the voice recognication will be ready only when you are not playing a game (I guess)... and if you need to use raycanting auido again you need to go to GPU CUs.

I don't see advantage here... both will be free audio processing without need to use GPU or CPU... anything more complex in audio terms will need to use the GPU.

It's a pretty neat chip, here is some more info on it:  "The audio block is completely unique. That was designed by us in-house. It's based on four tensilica DSP cores and several programmable processing engines. We break it up as one core running control, two cores running a lot of vector code for speech and one for general purpose DSP. We couple that with sample rate conversion, filtering, mixing, equalisation, dynamic range compensation then also the XMA audioblock. The goal was to run 512 simultaneous voices for game audio as well as being able to do speech pre-processing for Kinect."

http://www.eurogamer.net/articles/digitalfoundry-vs-the-xbox-one-architects

But like you say, the PS4's audio chip will do basic things fine, but for more advance stuff you have to go to the CPU and/or GPU.  The more free you can keep the CPU and GPU doing their things the better.  

EQ/Dynamics/Filter/Mix part is not for Kinect. It's for in-game sounds. As I said earlier, it's not that massive hit when it's done native on CPU, but they decided to offload it to separate DSP.

People complain that sony fans go to MS posts to compare, and do the same here... and in a post that no one said PS4 Audio chip is better than Xbone... but you felt urged to come here and show which is better.

It doesn't seem like sound processing cost much, I've been reading 20 Gflops at most, considering the ps4 gpu is 1.8 Tflops it's just a drop in the bucket. and if the run it in holes when the Gpu can afford it, it shouldn't affect graphics at all.

I'm sorry if I came across that way.  I recently learned about how the PS4 was designed how it could use 14 CPU's for graphics, which leaves 4 more for sound and other stuff.  Sorry, if it came off as dis-railing or petty. 

That's not fixed... the dev can choose how to use all the 18 CUs... it can use all for graphics or 12 for graphics and 6 for GPGPU (not necessarry audio).

Cerny said that about this 14 CUs rumor.

Digital Foundry: Going back to GPU compute for a moment, I wouldn't call it a rumour - it was more than that. There was a recommendation - a suggestion? - for 14 cores [GPU compute units] allocated to visuals and four to GPU compute...

Mark Cerny: That comes from a leak and is not any form of formal evangelisation. The point is the hardware is intentionally not 100 per cent round. It has a little bit more ALU in it than it would if you were thinking strictly about graphics. As a result of that you have an opportunity, you could say an incentivisation, to use that ALU for GPGPU. 

So if you are not using all the CUs for graphics you are incentived to use for GPGPU.

http://www.eurogamer.net/articles/digitalfoundry-face-to-face-with-mark-cerny

Except Raycasting Audio the audio processing uses little CPU/GPU... PS3 have the best auido setup last gen and it was made on Cell (to be fair it used little processing from the Cell for that).

The Jaguar is more weak but I'm sure less than one core of it can do the job but both Xbone and PS4 won't need to use it because they have dedicated audio processors... just something more complex will use the CPU or GPU.

The Xbone audio unit is strong (these 20 GFLOPS) because they need to processe any audio related to the voice recognition playing game... PS4 didn't need to do that.

Side note It's a coincidence that AMD launched a new tech for audio processing in GPU in the same day I posted this thread

So, PS4 GPU has 14CU's for Graphics as priority along with standard GPGPU uses and 4CU's are customized for more GPGPU(with more ALU) and can do Graphics as well. But, these 4CU's are does better General computing when used than Graphics so this can lead to better physics.