Closed tigaworx closed 6 years ago
GodCed
commented
6 years ago Normally, there is an audio file created for each source. I experienced empty files when recording really short burst of sound. It’s currently a limitation of the system because of the way the tracking and separating modules operate in ODAS.
Do you think it could be your situation?
tigaworx
commented
6 years ago Yes thank you! Short burst of sound must have been my problem. One of the sources was counting and there was a short pause after each number. When we tested again with fluent text it worked fine.
yesheysamang
commented
6 years ago @tigaworx are you using respeaker mic array v1.0 or the 2.0? If it is the 2.0 would you mind sending your config file. I cant seem to record correctly, thanks.
tigaworx
commented
6 years ago @yesheysamang I am using the USB 8 Sounds mic array. Maybe you could try changing the parameters fS and nBits in the raw block? If it is of any help: here is my config file for the USB 8 Sounds mic array: `` version = "2.1";
raw: {
fS = 44100;
hopSize = 512;
nBits = 32;
nChannels = 8;
# Input with raw signal from microphones
interface: {
type = "soundcard";
card = 1;
device = 0;
}}
mapping: {
map: (1, 2, 3, 4, 5, 6, 7, 8);}
general: {
epsilon = 1E-20;
size:
{
hopSize = 128;
frameSize = 256;
};
samplerate:
{
mu = 16000;
sigma2 = 0.01;
};
speedofsound:
{
mu = 343.0;
sigma2 = 25.0;
};
mics = (
# Microphone 1
{
mu = ( +0.000, +0.000, +0.000 );
sigma2 = ( +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000 );
direction = ( +0.000, +1.000, +0.000 );
angle = ( 80.0, 100.0 );
},
# Microphone 2
{
mu = ( +0.030, +0.000, +0.000 );
sigma2 = ( +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000 );
direction = ( +0.000, +1.000, +0.000 );
angle = ( 80.0, 100.0 );
},
# Microphone 3
{
mu = ( +0.060, +0.000, +0.000 );
sigma2 = ( +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000 );
direction = ( +0.000, +1.000, +0.000 );
angle = ( 80.0, 100.0 );
},
# Microphone 4
{
mu = ( +0.090, +0.000, +0.000 );
sigma2 = ( +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000 );
direction = ( +0.000, +1.000, +0.000 );
angle = ( 80.0, 100.0 );
},
# Microphone 5
{
mu = ( +0.120, +0.000, +0.000 );
sigma2 = ( +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000 );
direction = ( +0.000, +1.000, +0.000 );
angle = ( 80.0, 100.0 );
},
# Microphone 6
{
mu = ( +0.150, +0.000, +0.000 );
sigma2 = ( +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000 );
direction = ( +0.000, +1.000, +0.000 );
angle = ( 80.0, 100.0 );
},
# Microphone 7
{
mu = ( +0.180, +0.000, +0.000 );
sigma2 = ( +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000 );
direction = ( +0.000, +1.000, +0.000 );
angle = ( 80.0, 100.0 );
},
# Microphone 8
{
mu = ( +0.210, +0.000, +0.000 );
sigma2 = ( +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000, +0.000 );
direction = ( +0.000, +1.000, +0.000 );
angle = ( 80.0, 100.0 );
}
);
# Spatial filter to include only a range of direction if required
# (may be useful to remove false detections from the floor)
spatialfilter: {
direction = ( +0.000, +0.000, +1.000 );
angle = (80.0, 100.0);
};
nThetas = 181;
gainMin = 0.25;};
sne: {
b = 3;
alphaS = 0.1;
L = 150;
delta = 3.0;
alphaD = 0.1;}
ssl: {
nPots = 4;
nMatches = 10;
probMin = 0.5;
nRefinedLevels = 1;
interpRate = 4;
# Number of scans: level is the resolution of the sphere
# and delta is the size of the maximum sliding window
# (delta = -1 means the size is automatically computed)
scans = (
{ level = 2; delta = -1; },
{ level = 4; delta = -1; }
);
# Output to export potential sources
potential: {
format = "json";
interface: {
type = "socket";
ip = "127.0.0.1";
port = 9001;
};
};};
sst: {
# Mode is either "kalman" or "particle"
mode = "kalman";
# Add is either "static" or "dynamic"
add = "dynamic";
# Parameters used by both the Kalman and particle filter
active = (
{ weight = 1.0; mu = 0.4; sigma2 = 0.0025 }
);
inactive = (
{ weight = 1.0; mu = 0.25; sigma2 = 0.0025 }
);
sigmaR2_prob = 0.0025;
sigmaR2_active = 0.0225;
sigmaR2_target = 0.0025;
Pfalse = 0.1;
Pnew = 0.1;
Ptrack = 0.8;
theta_new = 0.9;
N_prob = 5;
theta_prob = 0.8;
N_inactive = ( 250, 250, 250, 250 );
theta_inactive = 0.9;
# Parameters used by the Kalman filter only
kalman: {
sigmaQ = 0.001;
};
# Parameters used by the particle filter only
particle: {
nParticles = 1000;
st_alpha = 2.0;
st_beta = 0.04;
st_ratio = 0.5;
ve_alpha = 0.05;
ve_beta = 0.2;
ve_ratio = 0.3;
ac_alpha = 0.5;
ac_beta = 0.2;
ac_ratio = 0.2;
Nmin = 0.7;
};
target: ();
# Output to export tracked sources
tracked: {
format = "json";
interface: {
type = "socket";
ip = "127.0.0.1";
port = 9000;
};
};}
sss: {
# Mode is either "dds", "dgss" or "dmvdr"
mode_sep = "dds";
mode_pf = "ss";
gain_sep = 1.0;
gain_pf = 10.0;
dds: {
};
dgss: {
mu = 0.01;
lambda = 0.5;
};
dmvdr: {
};
ms: {
alphaPmin = 0.07;
eta = 0.5;
alphaZ = 0.8;
thetaWin = 0.3;
alphaWin = 0.3;
maxAbsenceProb = 0.9;
Gmin = 0.01;
winSizeLocal = 3;
winSizeGlobal = 23;
winSizeFrame = 256;
};
ss: {
Gmin = 0.01;
Gmid = 0.5;
Gslope = 10.0;
}
separated: {
fS = 16000;
hopSize = 128;
nBits = 16;
interface: {
type = "socket";
ip = "127.0.0.1";
port = 10000;
};
};
postfiltered: {
fS = 16000;
hopSize = 128;
nBits = 16;
gain = 10.0;
interface: {
type = "socket";
ip = "127.0.0.1";
port = 10010;
};
};};
classify: {
frameSize = 4096;
winSize = 3;
tauMin = 88;
tauMax = 551;
deltaTauMax = 20;
alpha = 0.3;
gamma = 0.05;
phiMin = 0.5;
r0 = 0.2;
category: {
format = "undefined";
interface: {
type = "blackhole";
}
}}
Hi, instead of a real issue I merely have a question. I hope that is okay. (Please tell me if there is a better way to ask questions.) My question: If a have two sound sources can I get separated wav files for both sources? One wav per source? When I tested this, I indeed got two wavs of separated sources, but one of them was empty. It seems like the algorithm only records the loudest source properly...