Site Links
Howdy, Stranger!
It looks like you're new here. If you want to get involved, click one of these buttons!
Quick Links
Categories
Diatribes
Yet another miscellaneous thread from me.
Seems directivity is observable from listening. Picked up sb17nac's from Chuck at Indy25, slapped a .65 cuft box together and paired with seas titan (27tac) tweets. At first alignment had 1700hz xover, on axis measurements looked good, rev null check - 2nd order with tank on woofer, 3rd order electrical on tweet with a notch at 6k ish. Often feels like notching on tweets takes magic away when shoot for on axis response eveness. While sounded good, felt like too much energy from the tweeter for the sonic range. Redid xover for about 2.1k xover, 3rd order electrical on both sides, no more notches or tilting (series L or shunt C). Now everything sounds in place.... Makes me wonder about PBN designs where 4-8 notches, series or parallel. While yeah, know can achieve most accurate response, feels like need to let drivers do what they do sometimes.
Comments
I agree. Some drivers are better left doing what they do than suppressing what looks bad on paper.
InDIYana Event Website
I've discovered the same via DSP - You can try to flatten response too much and kill the life of the sound - becomes dull.
I like speakers used for listening to have some character - small excursions from flat response are what make each speaker system unique.
Build that XO to make your ears happy in your space and don't worry about the curves/sweeps being perfect.
I'm starting to figure out why this happens. Measures flat on axis, but sounds dull with no air. Measures flat on axis, but sounds bright. Measures flat on axis, but sounds harsh. Measures flat on axis, and sometimes sounds OK. I'm finding that I need to look at the tweeter response as if it is divided into at least three sections. 1) The top octave, 10k to 20k on axis, where most tweeter's start to beam. 2) The mid treble section, 3-7kHz or so, where too much energy makes the entire speaker sound bright and harsh, and 3) the overall power response over these same frequency bands. Flat on axis with a bulging power response in the 3-7kHz area sounds bright and harsh every time. Flat on axis with a drooping power response above 10kHz sounds dull. And all of this is generally due to a directivity mismatch between the tweeter and mid/woofer that needs to be resolved in some way.
and 3) the overall power response over these same frequency bands. Flat on axis with a bulging power response in the 3-7kHz area sounds bright and harsh every time. Flat on axis with a drooping power response above 10kHz sounds dull. And all of this is generally due to a directivity mismatch between the tweeter and mid/woofer that needs to be resolved in some way.
This ^.
Let's talk about power response a bit as we go please as I just got this Acoustas amp playing 3 times louder just by experimenting with the XO points and slopes - blew my mind but it sounds great.
I'm more than willing to go into greater detail discussing power response. But we need to be very careful and respectful in our discussion, as this seems to be a very touchy subject with a wide variety of strongly held opinions. Not about the basic definitions, but strongly held opinions about what is a good or "practical" way to measure and interpret power response information. Power response is simply the average FR of an infinite number of FR curves radiating 360 degrees from the speaker (the balloon response, so to speak.) And then there is the alphabet soup of various selected and weighted averages of the overall power response.
I think the problem comes when you ask the question: What are some good ways to measure power response so that you can incorporate this information in your speaker building design? That is where the fun begins.
Can we see some effects of the power response in the office axis measurements, bunching vs spreading and what they sound like?
Too much of anything…
Better to focus, imo, on reducing stand-out peaks.
Edit: While the miniDSP HD provides up to 10 band eqs, I often prefer to run (REW) set on the older -96k with it’s 5. Less is sometimes more.
Harman has done a lot of work along these lines, and their research is largely available for anyone who is interested.
Power response is not really a contentious topic - but the objective absolutism around "predicted in room response" is. This is similar to the Harman conclusion - that being said a majority consensus based on extended blind tests. Outliers exist, of course. Based on the target curve, 4th LR should never sound good due to inherent off-axis bloom but they often sound outstanding so I for one do not believe we have arrived at the answers just yet. I am still trying to correlate why some 4th LR designs flat out rock while others leave me wanting more. Definitely open to theories on that one.
That all being said, knowing what a speaker should sound like it still important so listening to a new design against a reference is still important. Over the years I have become pretty decent at developing crossovers largely by ear after initial measurements and a "jumping off place" initial simulation. It is rare that I am happy with the initial simulation, the recent monitors I just finished up were a rare exception to that. Smooth on and off-axis with very little "bloom" to contribute to "brightness" or "harshness", despite the cheap tweeter.
At the end of the day our ears are really all different - and our subjective impressions will reflect that. I am very sensitive to Sssssss and a lot of speakers sound a little to a lot bright to me because of that. I do not know if it is a physical or psychological issue. I just know I pick up on it.
I'll stop rambling, but I think further conversation is warranted on why some speakers sound good and other do not.
I'm with you on this, JR. Sibilance gets annoying. Some tweeters really grate on the ear drums because of this.
I've heard some "compensated bloom" LR4 designs, and they tend to sound a bit dull, and that is the 3-5k range. 7-10K is a range to reduce for sibilance.
I am very sensitive to gritty and nasal tweeters. It's like nails on a chalkboard to me.
InDIYana Event Website
There shouldn't be anything touchy about "measuring" Power Response. There is a standard, published a decade ago by the North American Standards Institute (ANSI) based on quite a bit of research (as you know) in CTA-2034-A and updated as CTA-2034-B in 2024 ("Spinorama"). If someone doesn't want to do this, that is absolutely fine, but there is no uncertainty on how to measure Sound Power accurately.
I'm not sure there is anything touchy about "interpreting" it.
Power response is the total sound power radiated into whole space vs. frequency. It is the total airborne sound energy radiated by a sound source per unit of time. Sound pressure, on the other hand, is the result of sound sources radiating sound energy that is transferred into a specific acoustical environment and measured at a specific location.
It is a subjective issue, though, how much (if any) attention to pay to Sound Power and even if you do want to focus on it, what Sound Power response do you want to target and how much weight do you want to attach to it relative to other design goals (i.e., tradeoffs/compromises).
David, I agree about your points regarding measuring and interpreting power response. But I think you are missing the point I was trying to make. I was talking about it being "touchy" because there are, as I interpret it, many differing and strongly held opinions about what is a "good enough" or what is a "practical" way to measure power response information. As opposed to the techically correct, and exhausting, way to measure and interpret it using CTA-2034. I think what we need to do is take a poll of speaker builders, asking them how they actually measure power response when building a new speaker system. And what are some of the short cuts that can be used to reduce the amount of time needed to make good design decisions. For instance, is it "good enough" to just do some quick 0 to 90 degree measurements with OmniMic, clicking the update average box 6 or 7 times, to produce a rough idea of speaker power response in your room? Or is it "good enough" to use REW's RTA moving mic method in your room to do the same thing?
Yes, you certainly can. The bunching is a concentration of energy and creates a bulge in the power response (or the early reflections power response, if you are looking primarily at the forward facing angles). If this bulge occurs in the 3-5kHz area, then you can get a bright, harsh sound quality that lacks "air" on the top. The loss of air on the top is often caused by the fact that most nonwaveguide tweeters mounted on a flat baffle start to beam above 10kHz. Measures flat on-axis but sounds bright and harsh.
Another question, if someone sees this, bass tuning empirically... Yeah get modeling look not crazy, impedance sweep match up. But more around the coil on woofer in a 2 way. Some of it coming from find right vocal tonality/balance but then determining if 'overbassing', like any symptoms or observations of when doing so? Though can vary based on genre and of course room effects that big elephant.
I have a tendency to voice overbassed, almost like a loudness effect. But in some electronic, yah like jazz easy sound 'nice' on even crappy speakers too, when get a little bit of droney-ness... that from too much L, or port tuning. Going to experiment to see if answer own question but maybe someone has wisdom. Know this can be tough to answer given bsc and room, but know there are probably red flags.
traw, if you are talking about the low frequencies below about 300Hz or so, then everything becomes omnidirectional and the power response or directivity curves generated by VituixCAD are of little value. Below this frequency, the SPL is bouncing up and down significantly as you move the microphone around, but the ear seems to average this out somewhat. Maybe take some psychoacoustically smoothed moving mic RTA averages to get an idea as to what is going on. Roy Allison did some studies back in the 70's that seemed to conclude that a dip in the power response from about 80 to 300Hz occurs when you place a speaker out into a room several feet from the floor, the side wall, and the back wall. Jeff Bagby has the Allison equations loaded into one quadrant of his Baffle Diffration and Boundary Simulator spreadsheet, if you want to play around with modeling software. The amount of BSC applied is complicated by overall loudspeaker room placement and the distance you position your woofer with respect to the floor boundary.
@traw - ultimately, you have to have your own set of reference tracks that you have played many times.
Sometimes when I have been tuning BSC, I can hear the bass and think it's enough, but if I bump up BSC a little more, it's what I want and expect. I almost always end up with 3-4dB of BSC.
One time, I tried "full BSC" on a two way, and it sounded sort of bloated and muddy, with not enough midrange. So, as always, "it depends"