Real old bump here, but as I mentioned in the other thread, based on some chatting with @tremblap this week I revisited the “onset descriptors” patch idea and came up with something that works significantly better.
Where the previous version was going wrong was that I was detecting an onset very quickly, then waiting 15ms (in Max land), and then analyzing the last 20ms of audio using descriptors~, with lots of Max slop in the mix. So not only did I have to wait a fair amount of time, but I wasn’t sure that the section of audio I was analyzing was what correctly corresponded to when the onset was detected.
So at the moment the onset detection outputs a sample accurate moment in time which will then be analyzed by descriptors~. The output of that happens with Max slop but, critically, it is analyzing exactly the right slice of time.
At the moment I’m using FFT settings of 256 64 for descriptors~, and in keeping the overall analysis window a multiple of the FFT size (as per @a.harker’s suggestion a while back), I’m analyzing a 512 sample chunk of time, which equals 11.61ms, which is also the latency of the process now.
This this is a bit faster than the previous version (12ms vs 15ms) but it is significantly more accurate in its results.
Give it a spin, particularly with live sound input (mouth/voice sounds are great for testing). The red subpatch p streamView is really useful for seeing the values over time. You just have to make 50 onsets before the zl stream starts displaying on the multisliders.
Let me know what you think:
----------begin_max5_patcher----------
8867.3oc6cs0iiibc94Y9UPHDXrqcOJ08pXrWCG6GreHNI.FHAAqCFvVhcOb
G0hJRTytytvyu8TWHoHEKRV7ZydZMX2tUSQIdpu5TmaUcNme4suY08w+T3oU
d+Kdeu2adyu7127F8kTW3Mo+8aV8TvOsYWvI8ssZS7SOEtOY0cl2KI7mRzWe
Wb7G8h168gvigYu4tn8gahOuWeGnzKdHHYyGh1+36OFtIw7jQ9j0LDlCEHFT
9SN8NOJCrVfw..W.Qx+lIVCtyCyWC79eS+l1e9on86BSzDF7xEiOmjcUP5Ui
1pIx36+g2gfYj28mu+9cg5Or5B+i29V0OtyQfXe3OJ+5pfCG71DGuyK371n3
iAIgdAOcXWTx4sgd2GbJbqWPRRvlO5sMLQN9iO1YrhwVK3kwJHQrV8KFRiQz
tgQPKXjeFYYtujOeHz73WcJ5w8A6Vk+.zjX3wTfJEodypGh1E9ovimhh2W3Y
7lUAGNT3xuovGQAu+Pr9KRbW9kh1atDH+RGC+TT1mGme0fiRfRgnmOpozU+D
ir5xWS71vi6OGkOWqmnSII8T59fmBOcHXi4Cql4yd6KPOTPT3KjvT+hCA5ew
KvRJ4YdbW7lOFtsHMuJ9P39n8GNFdRtxIHIk3ye6sgODbdWx6eHdexone1vQ
plJs79OjRhVeS0fPS++qGijyQY2xiGi1FuWQDklJTWN6wIGbT8XiVbvnui8A
Gr7gkbIRbol27jbPd9z8AGUyToKwPYuYhb4Q42J+ysK7gjz29Pz98WghIwGp
+MOF83GZ3yder7Mepoua86b58m2ad22KYJRd+ofOUFsSB1sKcge4u9eJXezS
xk6IQlo.DH+MC2GHGne3zliw61UZ7ZdmOY4c1JYx2D9iQaS9f9AUjYPd6QGx
XhVkOKuM5wvSIkuVRvimJekSIe1.5Etz46SWD+9jPovJ4nn7MTRGQwUrEEQV
55WIpzHDIe4XMB1.70JgYLNTKECj8yb9w5jmUub+qkqgEEIhLUYEGr5Ov9sg
+TAQEopFRkZzSLnj5hxpLdLb+W79CaOeTKZvCBAXWwJjVqHDoELgP8Crf1AK
+hDQa5AroKnLbTqNg5zKb0G2l9gZzQTudh10UTm9hR5LpSuw1SGVKmMK9kUP
+gzRF0zz6f.y7kOT+KJ4Jlb6ZQbPShKZSZUihiZUZPyhaZWZQCSqZYZUSSKZ
aZWiSqZcbPyiKZe5hFnFzB0plnl0F0rFol0J0nlo5zNYWCUMZobRSkcsUWKG
4ZI1Ud+Jd7rMrfAg4RyJtz328WkLnZ4.a+8WeiVjeC4ZSHgPe0uXLrV7M95k
GYOFaKQaR9dyx3uVNOy1HqFIGVUErpBQqfL82+eI5jzGmO6YVm9MRNlu8292
O922+eFbL3IuLUdeCg.AZ88xwy2AM2h5+i1u4XnRGs224Ikc58Om+QtbKO38
Mlucue224A79U+JuMeHX+igeSzd3258cxO329K5aNI81jWw7oS9GpeEt6TnW
gukeuG3a8t9Sj9h248M4jz2V7K4umn9oDYfxaN6aR+r+sqJBM4FRT1XhgxhV
w3hxFXHcKG1AtRzE6ut1jhprcf9x1UghrwW87icRppKfGAlGmBWPulWzBpG8
HMwVUVGqJxBsHPTOdT2Wy31o3yG2jM6jJ5vq5HTpHHIZet0IeeFEqu2dMi1W
5C1A5i0J8UFVC2FknXAt+wMw6LFf98RUh92U3GJYVW9Fu70MB9STNNbk4YOF
tyK4CRiD+fWw2uQi4r5lAjsVE6MLw2X9lQlv35SFDcMMVT2yLgXA2eJCw9lf
6Uq4eGE7sCB7HLfF7H9noC7nyD10f2qRSEOc5KdHJXPvED6qgKnPaLDGztGs
nZQKjczhCZBtbva26J326LwY9N7vvUrPnCU.1DpfzeNxbgKgkvuiLR.E0e5.
J5R.nniDP4CmNfhsD.J13.TjzvyMI.kXI.T7QBnnzoCn7W..0.EQQXqKHImL
AnDYIvNMPMdD55BhwmDThu.PIzfQIvEY3SBJsDjgCGCTJS.9jfRKASBFFHQ0
N3jJ71DRywFjHyDH8vtXIA4NZ7P7wmBzv.yQWoM6tYpyfj9gR03dCjTdh5nj
rSBO9dSP8uFdKghjlc+Q43y8A6ebbc6Y5.aNxXg5TB1zWVf8oMwGB+RKqjYX
spSrINvlP.CadO3KBOGUwcOKPXJQBV9jsuXWpXadhbwu9KCK5XoaBO0rstp.
7P6eHKpYS3QnAFxhQkIpAv72+EuA6F.1DwLZpVW7PBATc3I4EBdZhF4W7f.O
Hcb3SwZ+FDn1gUbWgUHv+EBtdZWz1PMrhPfgArPeC+JxDdbg+D.r7WJ3569x
nfkXfdUOdJV6K.uPvxfj3s2OPkSxk4ZdStQVpXBNfXB3qG7Les9ThmnWVxPU
mZC8OFGN0zMYDLE5mD3WJrp2eZjXTg35OHBCjQEunLhZxbiTxYWbGbmD2Hw7
uBciLC3FCGIemYmfeGtW9RRfioujZh008wN8.TQy9Y8ibPms1F14ilcuNq6W
xDjJmgnKPmsylSA.rxYxAQt9P4TyAxQ45qGzQt2tREp0ctQEjIjJDvtPEkuw
3iaMG0d3jPZZO5bedBLQHDzUtEC8NUSTJWv6.YflJ9EPmHiZXX.SBs4J6hJG
blL1EkcdNQEYq7lFp.4JU.lRp.1Ep.ZmWA87RZD3byF67RLDXtEIyccIlXJk
HyqxsTyBcxDREXW0KXQhvDyA4Low8maNHjqBl7mRU5tt3mWuzwzKlkPdqToI
012aRWr2GjjbL59yIFKVKlU5cJ4YebW78A6RS3nb2Isjasu8BwMN0PfvsOl6
ikce7wUpA.XoioLFCKfBL0GaN2YW66uKkC.jkxA.p1xAf1CyxdZNNXfJo+N8
g3jFwAJpJNvnWiCLRy3.x0xh.GVKN7vtXULEFQ.vjESckM.IXWO7SOTcnAWU
HX31qJDi23ea3tfO+EOJDo9+tBCTv0vP5IcZ3bAnYEFNE7gNyC.pHJvGMVCd
1jL3yxqyru7OEE9i5b1MZWTxmKRKwO7vovzA+6HlPCUXTYxa5sGkBmyyg0rh
.ylcQa9XxGNFe9wOT75URI1xuwmp9F2+3SoY3X9UtXTQ5UBN9XZDSV8GTY9t
VJ4wym9P3o0AQOn9y+vt33CJqoTu9Sw6JpWzcNc8LKLeKHsOAmQU45w1F9Tr
T079sqkSDxm0JmEBNmb+G7NkbLL3o+KI+PCqBPfp.CkIViKT.gDU1RwUkSbK
ACQX.hOAPfDhJCtjeVHR94E.eNVfzWBwIXBTHDbDkyRSwqFQ71JHQT3pWe0R
GSJOSDl.DyXlyKjpHOcqV5bqV5bqV5zm8N7f2CxIlV1eBAVeL0flr7lLEENF
nfz39SbqnwTm.xqDRRS2QbhQVoYtheqZwbqZwbqZwrbqVLWmlEkER+mh2KkY
k38vwv+uyg627Yuy6iR7h1mD68Tz1Hu8wIg5qcmWvIueLb2N0uk9tbPNS+nW
TxIOoD0CmS7z6R95qeRkJjj31KbEHibkzspmpOuHD9jU3JXyQ8PosIgMlIAU
03b+VC1JesB9aDMQsilFuLf9r09TJGf8S+GO67ghwOO0Dj4BZe3X7SdYKtiO
d5Bi93.sF9TewDiknEAapjwzSJWP5A7oXsrVyZ9ghjp5EHBKc9R5cr4eDUYM
ErV3yXHT1EE4mFuIDngbxBRhfWQovmFLNKQuJ3rPrVf4TJISzfJB09q4LJDy
xtFahwbvBnpTo4tAq0LdNTfkLIEhp36hulKk46V0VB26ZUEi+xnZUob.zqCv
oOYM9ZlQxnT6pZDMoKDz75CzWKIKMq9BSaimpuNBOh1KMZYa2Tk5t2kS4m6J
hqdF.mPHuRs.tk06RM8jqsjx0of9KfrzQwuBz5t4iNAsyV4ZSuvy4BhlVn27
Wx1X7tPiWeTWlGZT.6DNRcnzx8VawKpsy0v0AKqWNU274bv1Ycn7.XZSHBmB
pIAQ0o33zFUS7snZdKpl2hp4snZdKpl2hp4snZdKpl2hp4snZdKpl2hp4snZ
dKpl2hp4snZdKpl2hp4snZdKplMTXRbrziPMEXHHknZBtHJLULgPJmvznY5a
zMqqbVh6RcHYlJ1HsURmZqTbn5nVnBgEFN6cIwwEOd57tjHcwW5Xwm5ovD4H
PdmoYEiuobqbcASoQDR5ZujQiSxr+DnrU2OkSic02TVLMofwi+CLX9uYi26m
24osSOM2T7n.mYDssdFBwSPuNokZDy3CXtwbZXMINvalcP0et4L4eEyXlgwy
Gao3ENWY9NM9rKv7qX1xbPd93KQqVLv0wh921ZGZ6hy6bGJ0ectTiUdt5kl8
MF34YesJB+U7h0TLdFWptfVqdd+gfMeTEu2B+mS.FiWkmDxvCptxRcouPTST
2tygWTSoXYBJRfNWiXffot3y4RoNBlUkglNx.4DYPVBkhuouf.hetKgQNWm4
fyd4mxcZCM60TRgyUsqIbxy0Zf0TVg.ctPbglRAKTmKmjSobEgqkCrIjFbsx
5AguRKIYG7jFvHEOzwRQDjAWOlkfJrCUelWeESkRmnVFwTKUDfa0Rka0Rka0
Rk94X2u1CsdXMyJBdMxGxPrhG7LgtAqg7mfNEFr2c2lFbtaBbY927EOHFgAC
rqg3SpBuHDcMU9RLL6hbo7PwDzJgdozUlND+wvu3knsk4wgA3LzZdE.mwU0X
Mj.V7DAOnF3Bvg8MXBa.nMfkxUIaMk6zl2SEsEORNPsxXvDrkyjl2ZuYce3+
0d3gImTxQowKBTEOLLr3gJEilD4j3WFBJ2d5fxfkvA1OfH5.MhIYQZDBuvch
GB2IoN7s2Jhh1WNpio+s5Wu7DXBI9ZAlDPlrwYUfoO84Wh43npGJknhp.jym
p9WJsNL8Y3+Kdfw.ySUhIMWkI+GklA794xNF6dyn3UmEUo8SrYSh.kMSRDbo
MYYF7lD019AedfabMlLO8Hq9BRUNw312pP+ph9vXQUNFWvPXW4XvkzgrbZgX
9ttCGJkf00Yalls3vYRCSWpMnIwT1vybMX+Vvwmh1dHVZKXJSTZ87WEYPo8s
jL+Ff36z8.ypldU8NmSFC2G4ydGOxUJSo.Yd6STDmagUhkPuFxmN26nJtian
5BrKHo4p.yIWkNB.tKEB1jTHHWapFjSVCu1RYD1hGfVty4ssNh6xRJ3xbdAB
l8SUAv01dV9nXhniNnFA9Jbip+A4hyl5THvpsLJUWnfHshlREicGiBWemype
8IkvedavllZHPDSP8fDgxCdS5lRncafXoIkfL4V+XcXBTwRugAA0esTBIRfQ
.rt4sPQWOEQvMOEAbcJBxZZJ51gI31gI31gI31gIXz24vtuArH5ZBUPxKpE9
9S71LR5aHYG+cfTJ15TPoRDTgpCxCI5Tp3jGhxjRrtqT8gXW74s6keZowPxu
QuCQRf0S0b.8dJbaTvd4M7362HEYcLNZqDOSy9gmBku0oGdp7UJ97qqr4z2.
AC8khk..HBA3YZ8RKhYzQMT6jde3EF24Tmh.ZZPxUo7iBaxB4opyqMIg7jsL
i3Iw0f2wlPeOHt5ROw+U6ojUpw+bvtne1.IouesRDrtcmPxZFprGJLHVEz.D
Ux3SYJQCbgJLBbe.mKM0mnMItq9qPrXLLpHMWUtPMoa0c4oc0qO6kgl74haL
aFaJ0jTe+aFLeyf4aFL+loqneCMEu.AaMTZsjOofYwSSA.mdq9e+Fa0yoNV+
uIHywzwzd5IlCsCFvtU.vuU.vuU.vKNstfJ.3sTgNutbbUePL7WyoWcr8fX7
ZJm4ynYWDVWw5pQw3MKJuxwgZgTsNaqF9lD6opw.+yaTLisivbStkXppmbCH
NgkTRvRr5b6LLQLkca9DiRhk.HkUh9MQ.SWhOyh50kp1+kB1eVM.UU6nOe5R
U5dDpL+3KEiOHE80Pk4uEoip8jzi3.WI13DY5w+DXQVY6BDI8UfH5kQwf979
NBm9lcJjiUmZRLOuj6hFt5EZCRFaGMuqRzSd9Q2JddUed6vzmiEQwp6NDykN
igE94GMUbcNiMhZxK2u4cv6r57PqJ10nmZM4slkup57ZqAO2Z16M27fqIu3p
3Imidy0zVFWaGcpQm5bzwNWctyIG75fSds3nm6N64fCeN4zmSN94fyet4.nS
NA5nift5LXWcHrEmBcxwv1cNrcGDa2IwVcTrImEq2gwFbZzYGGq24QaBzro6
w584jop1MWcp5nTsZ6Z81u5VmkpUEbsaGay1xVwHgpFJL2SZN2BAZbGzaLwz
5SmnZBlJHK8oBmaTFCbpnsNW0Df8nE+x.25vU8F4GkNc0DLwbcWuZ4JgpwNh
U+mWF6Ni0jLGAdNmir59okUO16fV0dnm6SWzpwTp0MuPqdVh41n31BjxxaNv
dG2pY3uaccq9vZ2J5SeAf915NWMCrs0gtp8vuO.nrR25xwvpT4by0M6Pr2Yo
l4YHqMyqVD8zsF50THWuRy8pxTQ2rNuSSEUiwg0F9k8Yo5ZXU0LW4Ziqpobz
xVyqp2bYCl9s2bvZh9s0fvdFoeZmwetyz+U2z0gqzklIls35Nn3uzdyEy1IM
09fboGmeoMsTcZyWPx1yUb9w2hy+s37eKN+2hy+s37eKN+2hy+s37eKN+2hy
+s37eKN+2hy+s37eKN+2hy+s37eKN+2hy+s37eKN+2hy+qi37aSMS84BAA1r
JlFUu3dj5aON86hTX90O8lTnb8Woc4VSDJaUUQ8vLB2Ibt2I2Tk7dnH.1ThC
5D3UNKksJnuLlVm.lqP1p8gRahUZnokh6YlxzW5C2A5CVUf2jSenNPejmA5y
ReeskYXzrSg3NRgv4lButsG2.8QeNli6H98bPeHWWCKHOSTHzYJD2JEV3MKZ
LkKFR8KCshFztgS1LZ5x.XhKYfa1EFbrsxKCBj1DbTI5nfPfEJvLX9DzCbHq
luhumK8nkLDPNLqTgcljd1BrCEXmVqMenQDspFw4K7RQ6kuqZmHuXqpm15VW
pUjVSrVZcftfaKH+CrhG56uZd5bRIR4U.OWV5QT8uizpXAAInBQVsxWsUGlv
j02h6D1NJv4qbnyzk9KyXXt53TIdQdQCpzwRTMhf5vSLZHvIpl14k+.6AfyZ
O+KL3iCqSdIQOUQYjn1WHfOfjWHavY0Xj9ppnF1UezHfuyMLeL7P39sdmJq3
o6cVYeC2LghVSX9PNOCsQ24wmhJ+V+aAfyG3J8zWIecbPVa7wT+on4JRV7H6
uwCNJfJlBW6SD9PRA1UWD91cPkNDgCyEt9AoMRwpM+cbPWoopLgfix50NB9P
YYqQ0lOaooZqIOcjBakCVUkOG38OAGGsb1j65SmBFY9hW5f6F0BADeM9MiV0
xPeEaUqD3pGOmDqZY3WSV0BABP8lCLIl0xHudMq0mJpW75jXVKi95vr1bjc1
Lqkw9p2r1LPc9LqkweIXVqDWkhMoihlMqgdlBmBrs2se8G1EGL6NMHFId2Yy
oAN3UpSCWLhX17ZfuPD91zlFn5rTaiNcXWvmaG.YZlUJfuli7w43GjWWAddf
6H.kuZlfASsH1Mffh3ZFI63.eJvAxbgC4UhY2fBtohUaEI7ISARflKjHucs4
FRff51bpcjveBPBh+bgDwO7fTNr21+XKP.iX1kZtESEDSABvlsUEGCCRB8B7
zZ8e7XvSdwO3s87Spiy7mB1ctTF8TdSVIsv2nacLHApp9eShjvFYPa1DknRp
9DOUFiG1VnSQFglXd0vmvlB4ojYSJhBBzIkshg4oy6RhNsKR0ev64dxiXlDz
vmslesCj7oXS4IfE2lxySaxnyWzKQzuhidojOpV3bRBdIh8ZJ3kbe8QWZ9Bc
Ih+5MzkLiNy4KxkHwqiHWlAryVfKwe8ue7oX57E2R7qnsiOCbms.qg4uRCrV
lBtYKrZ3EhLWmN4xlVCJBulMKGbYTyGc6JI6VoSurKGf3F633OuGqAAb87dn
FP3mW2Bbpu0meZOnRc2UBM0jz55wn55c80Ds4blJxbiNo9RNiXCrNrooPulC
P34FfxNA7yHBApCgpMH8SRpV31pKiPm4CcP90gNMEv54Vp8ovckKlK8HUAfl
ySo8rdZJrfSza6JtOX+iW037V5Q8I2vjY6Hq8pJQLPPbs9KOIQ8gCeEef0.q
m0iqFG8J43pAVOqGVMN9q+CqlFRmuP9vIuVNpZoJzluSpFm9p5jpYXbmuyol
3UZ3zxrbX9NkZ9KdotV5z18W.Alt1GHPbQgNFADxGT.hn0r448ORk02RtK.0
4jZ0ZhzEz2VU.ovbPkp+gekZCWMk9Cki5Wciah2YZpDR3VWkBU+.j9JG4V5L
8xbjd8oKG5E5B8RpbiEnWfgTo.nOCdWN4W51iOt0zuQfOyiDTWQdaCBvzLHn
tx9PVFrODWoWbSzasrOSCQiGEYJyLQibEo4KBNCUotvM5k0KAKSGQCcknaFj
AyAHKbjdsLa7rAxbW4LP9KBNYkw+NQubxxgdcgoPEgiVV44fhP3y7f.tb0lq
pdRkqtd8RbBvh3jB24SQaOHcHII0haFjax+aezZJUvDYQJyjqm908lSE2HuK
lkA6BFLcz6nYbvLPut5vAFsLjN4pEtr1UYMKzqqV3xwKC70Uia4nkA9hFEqA
lO5E5J9tPrdA355M9xgdcQeAqQ+FJQpyu0KNOHHKWqWXtZmtEa0dNVYxb04M
KFz+b37FyU+JXX2n2I1uMlqVFwXKBIILWsLhQWF3Kc7rjaVnWmsLZgvO3rkQ
ftpYY5nWnqz6BPdFxQuc4fwyaWHjSMEwWat65y308lSIH3rl+me2cYnQQnyr
QuDmi3oX4DwShyQPjtH7wQSuXWXhEKBMQZ50EIOHWBaeFSwTCxtxSvGQokHX
5gOBtF4KnHT1ImQctj..SrAq9l1c6.8rhKLzLgKP.UXzh3Jv.dVAFDcl.FNy
ecWfE3yKrfmK9E+5dO6vBdRfErq5bvvEg04Xmi6Nc4PutXHBl3f2DU04LeKf
bdjf3K2fUgc144kwlzhcVrkX4XxBZDkoLeDsyBVDKBNCjyanGuWBVlNhF5JQ
+7GqBsMRnASucypAgfsttHUv3h0yZfJPzQYsLXVmwbVK0yefUPtJfGRWFqHv
tF8Nw3sh.CLkhQaqHf.PMu2Th.NejiV.bX3wamymC5E5pDmrvkMMTgqDQszv
k7b3Txm2UWhNbIaPNuMJ9ukDjb9z6+qg6OeIILjO4GBNuKwNke+iODsaW9D0
apbGuYUVJZjNcVrMhVZBF4SfPgZBFCwbDS+J4KnzqasplOGL6CRnDeUp9HeE
CwIT8qDHLEq4Vr7QQWdlJKOzOIfu.PLuJObqk+nA6ebmdjf3fhohhb58X7g3
iYyMxuB+Rety5Bf51nzxN.vZOS8tBLKGk2odZ6pNj4Jc4vr32gMls7I0+sya
BlhIx7ASCykc.WKOaJxmCEb.UHLuRPv09QymMYT4CSc+L0+3lWY91lkIyZR0
J4Z0+iCg689aA6O482BeJ593caWUujNBmBwZD.4iE9lWQg.leUUUAaT0.kRe
bLRtdPC3jL7PsJhX4SGtK7oq+3bgD5L3O.JDlWI+lPnpe96erzG0GPfb8iVR
0DN27QQ9luNJqzm8j7guQgxke5H4vTSyPFGYV.K..Ho5CWkpa5O66i1+ovim
ByY9v9HHyfZYRFPE4flzEcezTsZ+u+PTwh3ayK9r5AmssiXBn2mB9IlJaCcj
TsvvYVhlC57zU7Mxrb0vTxc31baSVALQfyU0rLmmIkKjk5fP9EW.pXDIT3bQ
5Ux+14PGPAI4YRgq9pVjjyEJ822Y8U1+nKFM5SGWb0Upcmi35JzTG3l0zaAa
sjnK1eN3jMY47eb24vhMY7NKlBC4Lhwnf7Agu5RvYbPbL9G2OnQwEZmlKSAO
yih+zmCF1f.fj1GXTVvwXjQx.BBg34aP7mOFFNvQgdV.q9mwfEkoqy2.3+Ib
2t3ebPi.gzrRtQ1JTXh+JUNyTUHaoDw+60ohO0G.DS8.87S2Gd7OKMWdPCS0
xCflciJMRgpGwvh5DlzAwQiAgpQQuj6xHLF1OcIBO0pZ4jjOtUCxmgAd52Q1
WvpSAeJb66krmRi6eePRxwn6OmXB+PgA4prxkZpB17GxpsQOFdJo70dbW78A
6zwPI7XNtl+1IAOZJGFqd6Emp0+zLunelEpnFFZnoFRQod8T10JU8L9Kg69T
XRzl.u+8vyYFXYsDZ.U04PeHUprDvzAQmRV666SgPNTnOwF5RTBjeYtzZMzv
dwN7hQF06+P5cVtEUTXTksv1eMXDgtrhy4vvOAxeMGSYTFGKPBnUDjfmcDLu
hJOgHnt3cNL3iJnqYbeFRJEgHcAlaC9LkQq4E9XSO7kUcOGFBhgRDDgkPEhk
AXUY.4yOBhGODrZW14R4Ypf0N9EnDa0OdDo8kpHhdyTfpJ5X9WVdI9g.t73y
0.kAdFBrrALtErPWlLRKBTWqBstMJp3TATbg+4njAKI736C2Gbug7KLjx7dN
6RQOtOVhe6h17whDl8RajQS6zLyVhy0lTXteaJwZbdU.eQNuBdwOwRZddEy7
UpG3DAESgT1qlkrB+W5yrE6ua1M7jztdquFW0l2BYWdSskpWeEbxnP2i3TCl
hnZIFLJRfQ.rQ6JDuFxjqZ84LyhWdkBKYWLDonruU8g0sT7lK3JPgdQg8Jko
Pyqx8Q9LCmZkQFl27HCYcjAsX3TVnDps5LNNypuStDbMC1z7IDIWeTdIJgfT
aeIV.EXoK9ltu7HMxy6IeMWeUGIl5fmNbJI9oSewp82EK+jVEeQsfM.5ZcAT
8BeR+32QV3241Lm9RMmrJjcRJuPMDlBv6PvG8Bje6e9TnWh9je7nGTJ06RGB
ninoEkATDaMw2mSk9HZXzj120LZRckSif5JZNpvWAwoeY7vKlXMFiA.tw0lp
k+TWX8r.VTbWAqzdRTO.reL3SgODe7ouzhzXhjq.BnDypLh+0rJXNQsC89.N
GlEWAJuM9l6O+vCEhfWJm8Jq.Eyh7qr67wiQaKu2No6.h7UJyMz65Gozo+oN
Qd203KLsxoQl6zfBeIegsO..5EWZU0lTlloDB4ijXQpnq7l4XmtCeTB2zzR4
5tqAFu93wkBlUqXIEOVb0cNBKkW7WkQGUl.G8mLn5SFN4O4xm+6qRZqocL6a
+IiF1SF5viFxub3G68Spb4VntAIZDdRTWdRPjc3DLCO5of4kfb3ImQdC5Igc
hakMFOIWFS5ANdnOInqrLvA9jtZYbCn2feRLGdRWs9+pyiuz6WoB+xFmgvzq
caBxPseaiMCuSCuxmI9wZUd4bkokBjwvdRtHOgMFqpQnNvsLnmDrTB4zD5Aq
kuDUkgifYq4DeAjI7ITSTaPLtC22Xyd3z.7JdnQZQAjMWZAfHGFjYkY5g+jZ
kyjMVOITaZADi0SB21SBT8QYLrO3vA0obL810OEo+P+fwKMwc5+LZu4O0tOr
5X3mhxtecSZaUvwMpCN8ljyGM9.8SLSKLY0SwRdw8miRYG0G3jqxsEynskbZ
4pSdyu715N5qYGUE64uRexckdl2J8LmUre5Vq+jsVyoZM63zb2aq+vAU9fAU
j0yRtnz+IfqOyw86j+1y7Moe4ZxnMIXI9.MmWI8JmR5e9jLjbIou4QxfxgjA
l+HCdAQ07Dw9BCGxMjASKkNY41Iidk2GtlyGc8jxOJC3B40QqHua4xwnPVk1
CswVVYmyMidlWF8Tx7HKrbj3pJu5vsYwh4YgCbWskaEClypZNT37xbmxahwh
.KleDNSgNkSDiDEVL2Gbl.cJeGFIBrTdM3NE1RtLLRDW4bVvcMMtjmBMmiBC
e.TIWDbl7c5X3OXBrRdF3fbGGysfdkWAca.YbgTu2YpQzoCAFWS0aw1a+Gu8
+GfxG3SJ
-----------end_max5_patcher-----------
1 Like
Can you explain how you’re patch is more accurate? I am missing something here.
The results are more consistent, I should say. Whether or not they are accurate… is another thing. But they do feel more accurate as well (when comparing ‘real world’ sounds).
The main difference is analyzing exactly the section of audio that is relevant to the onset, whereas before I was doing all of that in the Max domain, so being much more approximate with the analysis window.
As @rodrigo.constanzo explains, they will be more accurate for a simple reason: doing very short analysis windows bring their range in the ballpark of the Max slop. To be even clearer: Max’s slop is variable depending on the SVS and the load, so +/5 3ms is not rare - if you S&H your address after the attack with that slop, and only analyse a small window, on very percussive material, you can be within very different states of the sound you are trying to describe. If you do consistent sample-accurate S&H of the address, it is still imperfect, but you analyse about the same distance after the attacks, so you get a more consistent value.
A good test for you to make sure you understand: take a single sample (the same snare shot, no randomness) and analyse it via both patches. The ‘message domain’ values should be much more different between hits than the ‘signal domain’ one. I have not done that myself, but I did it elsewhere and it made a major difference…
1 Like
Ok, here is that test/comparison. I’m really blown away by the results actually.
Here is the old version (Max domain, with slop), run on the same snare sample, in a loop:
The centroid isn’t great, but the smf is a mess. Surprisingly the loudness is ok, but it could be because I’m requesting the maximum value, and that statistically stays the same regardless of the slop.
Here is the sah~ version run on the same loop:
You can see some tiny variations in the histograms, but the stream view shows exactly the same value 50+ times.
Absolute night & day difference.
edit:
What is curious is that the loudness reported by both is different. I’m wondering if the newer version is under reporting loudness since the window may not be big enough to capture the peak peak of the audio.
Next I’m going to try to adapt the bit of the code that created some ‘gestural’ data for each attack (waiting a bit longer and stitching together a temporal contour of the descriptors).
1 Like
which attack detector are you using? overnight i had a new idea (devilish grin emoji that does not exist here)
1 Like
I used both versions of the patch as they were posted in this thread. So both use your same onset detector, though there might be slightly diff tweaks between them, but neither uses the newer ideas you posted in the other thread.
Curious what you have in mind!
(evil grind full on)
This is it. The fastest, nervous, crazy, musical relative attack detector. It takes the slow fast one (my original) and the tweaked median filter one I optimised, and take the fastest of the 2 
Enjoy! It even rocks on brushes
----------begin_max5_patcher----------
3853.3oc6bs2aaajD+uc9TrUnnvtQVl6x20w8hatl1bHIMHNAEA0EFTjqjXL
EoNRpXqqH4y9M6CRQJQZSYQJETTCaJ580ryuY1Y2c1cze8nC5ML5VZROzOf9
CzAG7WO5fC3IwR3.4+ePuoN25F3jvKVuP5MQC+Xu9hrRo2lxSdd3LG2qQDcE
zwlJHLFg0P1H7.UDYfdVw883EFZfi00xRLZdZ.MMcwLpnezyOLsW+69iQAQN
EdA8mx1Jb9T+Pn038UrLwjzEA71tWukESPUd4LkoNyI0che33qhotoh9hA1X
fRejlN6I1j+ODx.EzexpxmeziXO5ucPGvAdCcBGWEHgqEj30X63a78x2XNea
nrUrsazzoTlXaE9NWAXTTXZh++i2Uw.UVGGT0KV1PmoB157XemfrblESS.x3
j5GEVfSz0sGn2GoaqxXBE4isC3TpG3zHpCHL5IfNrMG5TZYnScCfN6s.5rXP
mAQa2BcZFcHzQZNzog2JniMxQ2X2BclVcHzg2.nir0Pmk8NE5Lv3ND5T1.na
KFvZvM5XRT1sPmFoEftD2nYzuT0jfJ2GaCyKy5FJ36msIxDigoOkSkxqfVgJ
rMPhlhXfHgOcCVUI+i1ETL50Pt6XKdW3XMk1gCUIFCLANTkX1JbXciXf9cyG
yn2.yMst1uNlCDZhEGRr5DCGfbaCfA88GLnhM6RXPeSfAi8HLnY2kvfwl.CV
6QXvB2kvf4F.CpZ6QaCXsNDFlR8Pi7CRownzIvTiS1.P4guzVCUMwVh02IKx
nL4v5JaETNJHBnbk3jVk3Do1Mfy79P4MgeGPoSLjNHnthF5LT.EJMClMMaNL
OJJdpCu9FMD3I2OvK5.RbWaWg6p6Mb2VgsXx8HtWpCrk3dMtbRXt3KHbcNmy
tV3OwebH.vUCHpaummzsUD7MemyxoQZYOtcbUqnd4Bs1LdlzZ7La+T5FDXkT
vd35DFeLM7KavjDMGQZ4oVuKOSJ1rops7ikvTw5PikfiDcfdne.8Sz3DXzdA
JbPOmYyJj7AEpBCR+XTbAODyRxOTjjZdRwzO4mUe87TchgddJzsmGK3zaMxV
HBqYh7nwgy84cEQhfv8QYMXFyh04boImK0Eaq2z1dI2B5AiciBDcI1VYs6W3
AtXAod9oLnrwUX33fH2qodELZBZByng9gEscVJaO5Hm4AoWUR4BOnx7G43Rq
sxUpLcPuww9dQgrNQIgHK4LxAnlXKoJEYFdIBclUQkAUc.vqIyDfImmLzIlI
ikyfPxxLMJJnbV40KfNJUl8L+vvUPwznY0mYr+3I2QcGFAYN8tZadNIWMOTj
6UfUgzqRb9TYzN0IHPZlnbyeqSnOLcFM0WHBHJ4YJlEcRhabTPPI9UjympHG
OX3gK8FeuzIbBUTY.Jt+rLknd4RYO+wzjzxok5LNobJqYDARZ9P4v+qRoSmE
.bQ4BT53tJNVunA0Rou1Zw8nrR1eY90nqu5TpEqx5KpIWScMqoO4UfZYxLXv
h2OVrMpxvZM3RsFXyo1piEqahJ9HKUUwrU7YnMrsJLNiUOFDwI+IeO5x3KCu
LE1nhuSnbuJ8kINzIA1+RTHJY9LZLXSJvGrIhJUVzvEnON.M000INMjtPV0i
Y+Hdk82ErF3YYMPL0I.wzcQNy87iPIKBSmPS7Sf2R.shKCQvOOKZ1B9.Mzgt
GwTwIn+Cf3InW49LAsFfNOH.wKSBhYuK9STuAL5AiNm8CmbxM2by.NI3TX.r
KMHSdi+tI.0lEGMFV8IBdcTLkhRhFkdiSL8Tzhn4HWfGiAVMIM1e37TJxOE4
D5cRDf.Qd9iVHZIH04gd7M3QQ.fLMAEMh+O+xqeO5WngzXfaey7gA9tnWBiy
BS.9FHNKkjI..OT1Rr57bV+3BY+.87Hno4lvOEQ8g7iQxYBQjLpHax9nnXQy
bnSJq+Gih3iaOB5zKPrwY4UdPcnvRl0C4Gxa9If8V3EnMAF8Fe.uGRQySnil
GzWzHPwQ+9Kd2u9au+cnye8GP+94u8sm+528gSghmNAznQvr5hFyGFv6CsMv
bwNgoK.dPzFu5me6y9UnRm+Su3ku3ce.3Ezyew6d8OewEnm+auEcN5Mm+128
hm89Wd9aQu48u8M+1E+7.D5BJqqQEMwcf1i3hL.O8noN9AI47+G.wbBzEC7P
S.iuf31k5C5PHGjKn8c+BRQy3.acZLmaghuDQOE4OBEFk1GcSLrNCTZz5hXQ
CrTN2G8hP2ArCmDJmS30AfX3hTnFPq7b+Q.EddPTDLB8mhRRYE+UmiTHXrxw
XUELB89KN+xvu+D9HO3u+sSpC5SNAGpqbTejyXJ6kSY47qfnNJdAZ5gxDdCa
iXHlUxCgkY.FtNi.e3b6YY0fMGE5LdIPGiv7zlEk.Icr3efEcLmUB+Pw+m82
ImfbClOMYAjiOvGL8wgfsUPg7FmE+KYQ.rh2ztSXdFOAcCUHS.TKlxpHq6yI
ynC4E7aNCM8HzeILx.h3Cu9LkSQW+DO+oGBE8H38GeFNuDWlNK5ZJKm9nqge
EL0koel8A+wTI2k24YMpOqQ8eBOcjewFjIpOeLEpzLJ8ZQC6m0pPmLO+yPLn
qTGggZ9E6.WlRC.M07hjU4GelDoKy.xrKPvkrA6ual.qk9PDPnu4LEzxtLkK
B48WPqnOq.GiEMAh2oExvmfXkbUniWCVF75cTEcqk.gngWqfIniWxPeFI34g
v7AWeZUL.qBeyJvWU7viKwCHAS7isAS73JYhG2LlXIA48nBMzRpoTt4gmfES
bIFjqteB4niJMppW1z478cJ2dxCbISk1KZ48iB1eva9RovOzkRUZuDqsFJks
XMT0tVIqB9+EmsY9tGXYSL9.PVsdOLnaSW9YiVloo3h.npemf2xs3AylU2Z6
4zfke0nZBrfF2L8GoFFp7hZg8p.6dNeCu+Q9h5QMUlto8A8F1GzpsOHSTjxl
5.o4SGRiy7Nymbhy0DJmSAkGh0F3y1p7LK9tbYDz67mNeJ2IKJ05FInhYkhr
wNdUbiSTUrYdgSSwJ26qEcuDaezdW4jJWJ6x2RV0iSf404znQq6Vok7Naocq
.r+AV8OW5mnkEEVIYbZ0BgRkKC0UpHuo.7vAgAUmqysB3sxrYqRBrArt7ppR
IPT6kiYkpkOHcQXaYIvzYq4MS9B09VbU9x8NN9fNyKtY5O.9YZgIXXgtZ16L
2WSL2atulnXJNzWCt2JI7KbYayzNoQdCqjwMZLiWyQ9PrDmVKoMuxY2EdkSO
9Q7nY0EJIR6kegwIvOUMJgnusHGVWbLEZ1M+lWsE.WF4DdEGi2tqicclU3.l
JNWshMmsKrG5zhbQQXTaOXrQSWq.TH8Kmd6pB4MLMxoB8Fr8lxv31fgE1REW
yHsN43wp0FC15gYbE2dFW22FKvp6u4WDm0WKMruNY+vjpj76OAOFFNytJoXw
HcUyt5.gQO0adL2xNz7JUcc.r26Z+x0VIuso+s87dME22giwJhXtvVb+wz0T
953jbI65SxUOKJj9mSx8eNI2c6I4RpyIYFci6G2QGgqLHFwhn0vvfeVtDU85
ND2rixQL74PPnW7Dcxl43PMMrB21L6rcvKclrenaLkc6UQmwsIcRdUVVjQnC
EsN5ImgTPe22IOllC8CwGwNgC7QR2rKKVAGjy9f6i7BsxOhTxcLedMjubL5v
7tzQkOijBtGOqk3z9z8jyvefd7tK8oclxi3tWsRXgtG7pcctttKcNsDCzvVU
srrul7NsQG5cZi8p2oq6FwGSCjWEdTyuli38PvCQDtJSyRqMtU60AGvdZ13H
CXeDBQ1hflCapzknwlDIUZ6iXmgGEiDaira7cWD33aBFXtOBblAKisvNBCHa
BFrWBkLgy7r6PL.uIXf9dCCjN9QauGS16gXHS3sKMYfDauSC6IrVmG9Mcefz
HmiUFII63.XBq+2.DTEy+B.ocPvZCk8k1iaVj52RAxNryW1TMJZsRXreeAZk
B76FXvAqX21wdiZ64MVcKo2I6BWRmvtF2bDqn2nueHy7qQDCqaIVZqMe2hV1
cHhwbAC+QywLK0uF0xrkechH9trQgrUX1FG4ol+Mvvc1WCIxcT0py8Uzxs5V
diu1gSkIryW73xa8KNvnX5+cNMzcA5aw8Q07U5FAuGts.RtWDloXrZWXERDw
NdTlgCzSihYQshJ5ov7eyhXwIwD+wSlAsA5ooQyhBhFufEbGPUtIJNcRUm3b
8iD87cY9YxIdQ2cziYqLPbgCTM5DPy0Iw0wq5u1i1eG3NNygLhcdYrcG8rfl
UvgpVcl60jKTwTbyqEKtSs3BGy1TXwl2Ozida9IztgbIu+WkVL9gIFUZiaPf
MWLJt4HD8rmaNHvqQYWXKvjUcarDYV+xLy7CrQNgq1WwruzGP0oisQTR+9nD
osnj18PI1khtcnj58PIrdaQIx8QIs1hR36SNY1VTR49jSshtGtATRuMPOlur
ueJUtP7ojq27VSIMwnAj1nZJqrcT1rIBxNgoyLMc23ssXvy1QIRSoDda0Vsa
.kraAkUrUCHjV2H2TZJow6jQj1cw3hFgupJcAo0T2.RucC9ajRTaXEuQlY3N
naOIJWoClSZR2aWmSZbaOJE2DsHhQaHa0ahrsMVyFtIVW4cGbaKIsZBbhaig
JlMlI2MvoV0voR2SZNb15CLTajonVYNZkc0pAHMYQx31Xg+3lfd5psvj+XbS
ozVuEilL1tMre0jIhVwPSKMdqIT1ztKVsXSFBn1JSNn03kXr0pl5MlTa6VWH
MZZb7Z3mv6RqDXFLhrR.YrRvXrdfXTePXrZ.XvC9Bgu0VwiV4GmyTmaMxue3
YQzPYDf4FWdHXbkeHquW7XpW9nPnXT9aqOrLW4CkAKcakiqKMLsT3cXwJgkp
MAavdyTw1RQS15OZY7jvNmEnpq51vdSgdue1fyhR2RLbAuXVMKWpKoQT0I7H
NQ0jnqweiXpoia6tUoSbo8jEi7CBxYnhAOTlSZ6MN1wye4kGRx+3bYhA7iY+
JeqTD3vqFIqZlVV.x0ux2VuZY0hXqfs4xdUorm8FjDdkZ4DNVFdKlEhQiYwQ
yhhyiymAp14kedZTNilY9N+h4Vs3q7nilIEKdP.MP6hKyz.0JEB+MfmUsaSM
qTmY2Umo3g6BFudoSZD5krH5o2Cg9Pc97i9+.DQqJ6.
-----------end_max5_patcher-----------
Thanks for the explanation. For some reason I thought that everything was in the signal world until descriptors~ for previous examples.
Cool - new test for Rod. Play a snare by hand as consistency as possible - compare the two patches (i.e. what happens in the acoustic world, where exact repeats don’t exist.
All of my sound cards don’t really work at the moment (!!), so hard for me to test it with live audio, but I ran some other training data I had with more similar hits. They aren’t the same same, but are fairly consistent.
It’s a loop of 7 hits.
Whoops, here is the old (Max slop) version for comparison:
The centroid looks alright here, and sfm is a mess again though. The loudness does look better, particularly since the snare hits are all quite similar in dynamics.
Hmm, definitely need to improve things there.
What’s surprising is that the window is big enough for the centroid to (appear to) be meaningful, but the loudness is way off (or rather, way inconsistent).
Here is the audio file I used as a point of reference.
snare hits.wav.zip (520.3 KB)
Ok played with it some more. It seems like that the settings for thresh~ have a massive impact on how the loudness is reported. Using a thresh of 15 20 produces more perceptually relevant results, where as my “standard” settings of 10 15 produces more erratic ones.
The first half here is 15 20 and the second (right side) is 10 15:
Where it gets weirder is that if I start and stop the audio playback, loudness reports a really loud hit on the first return. In the second half of this you can see me turning playback off after two hits, then starting it again. So it goes LOUD soft LOUD soft LOUD soft, even though the hits are fairly similar in dynamics.
One thing that sticks out to me is that you (@a.harker) specifically mentioned analyzing a window that is a multiple of the FFT size, so I was going for a window size of 512 samples (with FFT settings of 256/64), which turns into 11.609977ms. If I try to analyze a window that big, Max averages it down to 11.61 (as in, I can’t make a - 11.609977 object), so maybe that tiny bit of a semi empty frame would have something to do with this?
edit:
One more point of reference. The first half of this is a quiet noise~ burst (0.01 in amplitude), and the second half is a loud noise~ burst (1.0 in amplitude):
The idea here is to try on the exact same signal. If that is not consistent, then you cannot trust the patch since it should be. You have proven it is better with the new one, so stick to it.
As for thresh and varying signal, it makes sense. What you should do is to take the new fastest version, and listen to the sampled grain by ear - that is always a good start for me (I trust my ears) to identify if I get what I expect - if erratic, then I can troubleshoot before descriptors.
Also, be careful with @a.harker descriptor object. We have in other thread talked about errors. In my performance patch, with the current version, I sometimes have to re-send it the fft parameters to reset it. @weefuzzy had similar issues in his. It is a hard bug to reproduce, but again, it was affecting energy readings quite a lot so it might be that.
With the same exact signal I get consistent (but not the same) results from the Max and MSP versions.
I’ll try listening to the grains and play with the window/delay a bit more. I figured that even if the thresh was reporting a diff slice of time (all inside the MSP version) that grabbing a bigger window and/or waiting longer (or less) to analyze it would make for more consistent results. What I tried so far on that front didn’t have much of an impact but I’ll do some more testing.
I do remember there being some talk of problems with how loudness was computed, but it was odd that the Max version’s results looked better.
what I saw in the graphs were that you had a lot of variation in the Max one, and much more focused values in the MSP one.
the bigger the window, with consistent distance from the trigger, the more consistent I would expect it too. but again you might reach a size that makes it too big and starts to grab stuff elsewhere (other sounds)… a typical loudness measure, from the ITU paper, is around 400ms to be perceptually accurate… I recommend this kind of geek paper if you want to see what the cutting edge commercial algorithms are doing:
“LOUDNESS METERING: ‘EBU MODE’ METERING TO SUPPLEMENT EBU R 128 LOUDNESS NORMALIZATION,” n.d. (https://tech.ebu.ch/docs/tech/tech3341.pdf)
Don’t forget that I highpass the signal too, so getting energy might be problematic if your signal is low-end heavy…
if you run it again, you might get different results. That is what killed me in my piece - i got the bug, then ran it for hours without issues, then got it again. The fft trick saved the gig, but it is a strange one…
Yeah super sloppy, but the loudness even in the Max version was consistent. (surprisingly perfectly consistent)
I didn’t do that at all, so I’ll try that. And actually, I can probably pull up the bottom end of what I’m analyzing for in descriptors~ land as I’m querying for 10 20000 in terms of frequency. If my math is right, an FFT size of 256 would correspond with nothing lower than 120Hz anyways, so I can chuck a hipass and then query for less inside descriptors~ too.
1 Like
be careful
it will still represent the full signal, just not with much precision in the low end for analysis. I think loudness will take the energy in all bins, including DC, so it should not change much. you can send test signal to it at different fft and it should not change amplitude - but if you only get a part of a wave, yes, it won’t represent the full energy. that is why they use 400ms for loudness in EBU (but then they have filters to represent roughly equal loudness contour and such)
So I’m working on a version of the “onset descriptors” using the new fluid.buf...descriptors~ objects which I’ll post as soon as it’s done, but there was a lot of chatter on an older thread on the Max forum dealing with this same problem that threw up some interesting links I hadn’t come across before.
The HandSolo: A Hand Drum Controller for Natural Rhythm Entry and Production
Real-Time Hit Classification in a Smart Cajón
Hybrid Percussion: Extending Physical Instruments Using Sampled Acoustics
2 Likes
