From a8c039899bc0fba9ec1eae88c0a1126b5fa499db Mon Sep 17 00:00:00 2001
From: Maxime LE COZ <lecoz@irit.fr>
Date: Tue, 25 Feb 2014 13:09:11 +0100
Subject: [PATCH] New Start session localizer IRIT speech & music detector
 modified to use frame_adapter

---
 timeside/analyzer/irit_noise_startSilences.py | 193 ++++++++++++++++++
 timeside/analyzer/protoStart.dat              | Bin 0 -> 572 bytes
 timeside/analyzer/protoStart2.dat             | Bin 0 -> 329 bytes
 timeside/analyzer/protoStart3.dat             | Bin 0 -> 329 bytes
 4 files changed, 193 insertions(+)
 create mode 100644 timeside/analyzer/irit_noise_startSilences.py
 create mode 100644 timeside/analyzer/protoStart.dat
 create mode 100644 timeside/analyzer/protoStart2.dat
 create mode 100644 timeside/analyzer/protoStart3.dat

diff --git a/timeside/analyzer/irit_noise_startSilences.py b/timeside/analyzer/irit_noise_startSilences.py
new file mode 100644
index 0000000..2128bbc
--- /dev/null
+++ b/timeside/analyzer/irit_noise_startSilences.py
@@ -0,0 +1,193 @@
+# -*- coding: utf-8 -*-
+#
+# Copyright (c) 2013 Maxime Le Coz <lecoz@irit.fr>
+
+# This file is part of TimeSide.
+
+# TimeSide is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 2 of the License, or
+# (at your option) any later version.
+
+# TimeSide is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+
+# You should have received a copy of the GNU General Public License
+# along with TimeSide.  If not, see <http://www.gnu.org/licenses/>.
+# Author: Maxime Le Coz <lecoz@irit.fr>
+
+from timeside.analyzer.utils import segmentFromValues
+from timeside.core import Processor, implements, interfacedoc, FixedSizeInputAdapter
+from timeside.analyzer.core import Analyzer
+from timeside.analyzer.preprocessors import frames_adapter
+from timeside.api import IAnalyzer
+from aubio import pitch
+import numpy
+from scipy.signal import firwin,lfilter
+from scipy.ndimage.morphology import binary_opening,binary_closing
+import pylab 
+
+		
+
+
+class IRITStartSeg(Analyzer):
+    implements(IAnalyzer)
+    '''
+    Segmentor MOnophony/Polyphony based on the analalysis of yin confidence.
+
+    Properties:
+    '''
+
+    @interfacedoc
+    def setup(self, channels=None, samplerate=None,
+              blocksize=None, totalframes=None):
+				  
+        super(IRITStartSeg, self).setup(channels,
+                                      samplerate,
+                                      blocksize,
+                                      totalframes)
+        lowFreq = 100.0
+        
+        self.input_blocksize = int(0.02 * samplerate)
+        self.input_stepsize = int(0.008 * samplerate)
+        
+        
+        sr = float(samplerate)
+        highFreq = sr/2 
+        f1= lowFreq/sr
+        f2= highFreq/sr   
+        self.filtre = firwin(10, [f1,f2], pass_zero=False)         
+        self.energy = []
+        self.maxenergy = 0.002
+        self.min_overlap = 20
+        self.threshold = 0.1
+    @staticmethod
+    @interfacedoc
+    def id():
+        return "irit_monopoly"
+
+    @staticmethod
+    @interfacedoc
+    def name():
+        return "IRIT Monophony / Polyphony classification"
+
+    @staticmethod
+    @interfacedoc
+    def unit():
+        return ""
+
+    def __str__(self):
+        return "Labeled Monophonic/Polyphonic segments"
+        
+    @frames_adapter
+    def process(self, frames, eod=False):
+        '''
+
+        '''
+        
+        self.energy += [numpy.sqrt(numpy.mean(lfilter(self.filtre,1.0,frames.T[0])**2))]
+        return frames, eod
+
+    def post_process(self):
+        '''
+
+        '''
+        self.energy = numpy.array(self.energy)/max(self.energy) 
+        silences = numpy.zeros((1,len(self.energy)))[0]
+        silences[self.energy<self.maxenergy] = 1  
+        
+        step = float(self.input_stepsize) / float(self.samplerate())
+        tL = numpy.arange(len(silences))*step      
+         
+        prototype = numpy.load('timeside/analyzer/protoStart2.dat')
+        prototype2 = numpy.load('timeside/analyzer/protoStart3.dat')
+        # Lissage pour éliminer les petits segments dans un sens ou l'autre
+        struct= [1]*len(prototype)
+        silences = binary_closing(silences, struct)
+        silences = binary_opening(silences, struct)
+        seg = [0,-1,silences[0]]
+        silencesList = []
+        for i,v in enumerate(silences) :
+            if not (v == seg[2]) :
+                seg[1] = i
+                silencesList.append(tuple(seg))
+                seg = [i,-1,v]
+        seg[1] = i
+        silencesList.append(tuple(seg)) 
+        segsList = []
+        candidates = []
+        l = len(prototype)
+        #import pylab
+        for s in silencesList : 
+			if s[2] == 1 :
+				shape = numpy.array(self.energy[s[0]:s[1]])
+				#shape = shape/numpy.max(shape)
+
+				d1,_ = computeDist2(prototype,shape)
+				d2,_ = computeDist2(prototype2,shape)
+				dist = min([d1,d2])
+				
+				candidates.append((s[0],s[1],dist))
+				#pylab.plot(shape)
+				#pylab.plot(range(decal,decal+l),prototype)
+				#pylab.show()
+				if dist < self.threshold : 
+					segsList.append(s)
+				
+        label = {0: 'Start',1:'Session'}
+        with open('out.lab','w') as f : 
+            for s in segsList : 
+				f.write('%.2f\t%.2f\t%s\n'%(s[0]*step,s[1]*step,label[s[2]]))
+				
+        with open('cand.lab','w') as f : 
+            for s in candidates : 
+				f.write('%.2f\t%.2f\t%f\n'%(s[0]*step,s[1]*step,s[2]))				
+				
+        segs = self.new_result(data_mode='label', time_mode='segment')
+        segs.id_metadata.id += '.' + 'segments'
+        segs.id_metadata.name += ' ' + 'Segments'
+        segs.label_metadata.label = label
+        segs.data_object.label = [s[2] for s in segsList]
+        segs.data_object.time = [(float(s[0])*step)
+                                  for s in segsList]
+        segs.data_object.duration = [(float(s[1]-s[0])*step)
+                                  for s in segsList]
+        self.process_pipe.results.add(segs)
+
+
+def computeDist2(proto,serie) : 
+	l = len(proto)
+	r=  range(len(serie))
+	serie = numpy.array(list(serie)+[0]*(l-1))
+	v = [numpy.mean(numpy.abs((serie[i:i+l]/numpy.max(serie[i:i+l]))-proto))for i in r]
+	return numpy.min(v),numpy.argmin(v)
+	
+def computeDist(v1,v2,min_overlap):
+		'''
+		
+		'''
+		m1 = numpy.argmax(v1)
+		m2 = numpy.argmax(v2)
+		l1 = len(v1)
+		l2 = len(v2)
+		decal = numpy.abs(m1-m2)
+		
+		if m1  >= m2 :
+			fin = numpy.min([l1-decal,l2])
+			if fin-decal > min_overlap:
+				
+				v1_out = numpy.array(v1[decal:decal+fin])
+				v2_out = numpy.array(v2[:fin])
+				d = numpy.mean(numpy.abs(v1_out-v2_out))
+			else :
+				v1_out = [0]
+				v2_out = [1]
+				d = 1 
+		else :
+			return computeDist(v2, v1,min_overlap)
+
+		
+		return d,v1_out,v2_out
+
diff --git a/timeside/analyzer/protoStart.dat b/timeside/analyzer/protoStart.dat
new file mode 100644
index 0000000000000000000000000000000000000000..463f177e7703b1d01e4c272b5b137150c1f465ae
GIT binary patch
literal 572
zcmV-C0>k})0%LA<ZE$%mV{dY0E^T#ebZKF7a$$K2Uvgz*Z*FsRa&=>L3UL8rZgp*N
zc?xc1VRCX|c?xj?O8|vc0b++zaRVqz0ZTW9V{UbAaCr)3ba`-P3ULHg0%kZ%080Uf
zQgH<+O9NE_JWftdO8@`=|4RS=|Nlz>bYh8AxB&nFkq#!WgTA>xGmOpRySueNO4O(L
z!O5#X-c_`@abmJR{QOwmr<bxn>D{o`RRyp=qvvi9EuN=8H2W?Ns@bJKc$ntvw}YZT
zKbxXh%OR#e|I7hMGzO?YVvM{38(646Dqxa)$*iV7RsD*h9uTHKe~%bMpB$z?)u<N9
zSQ)cF!%F&Fb7{9f<@T9Q3>>#V_eebY^S-h_MEOh;^dhJ~_bDnSH&3TOeg$z=l+>j^
zN*4I(6F#OtYD~t^is+|5No8j`{%@y0^~5Sbd-kb6IB#q(5a+Ewp(^+t4kFk;-G|JF
zm5km$`XSbK$8g|3D$$<UX;jreN2?qHF7N3-+qa{_;l%Gh00000008hmt*N>IfBxY=
z8c(ylnQh=dJ0aZB$urVF3ledV!NkHpNCf!m^Y6kxsZQc1_QJ<Mds;|?;r7NqJ4JEY
zO{2j-yl69qJG8Yw3sr&qWQndn*&{MYQ}M1pMmF7tIZ3lW@GgbmC{naPcJ|yn8zZzo
z6fsEopS83<8o5Ro<E^znLsT(F%;3L2T-m7_rJle)YH+As5kbB`cYLqgS8%XDec#P}
KMK7^GbYd>y{t5a3

literal 0
HcmV?d00001

diff --git a/timeside/analyzer/protoStart2.dat b/timeside/analyzer/protoStart2.dat
new file mode 100644
index 0000000000000000000000000000000000000000..3f061271492929fe06ff5240aadd60989fc68ccc
GIT binary patch
literal 329
zcmZo*O3o|IEvVE>&M!*U%Pq|*$xJLNO049HFG@|$&nqq|DorloDrAJH;>t^b$QCkr
zGqi>>Cbb6@GHZA<dP}xK6{M6@7Nl|&vV=0FS$H#eGXfQ`YIrk;GTQk0`FZ^Z0x;pt
zP?FRcdg8mLmYTW$a{D^g!q6#KmfCxX{dg&Cx6D4v=h%g=7t8HEQ`4>f<uAAYdPK{i
z`rAr-i~JmYf#+-O7i#^G<x{$0f4BWi`_!I$_P-Rbl^rj5V6Sy?-i^$VtM=}zWtjBd
zzqG%-eet1(N8Z~rfWZg*wJUcq)c<>EFXg{^&&=Eh_STAbE}k^LWX~;BIN{)tL-rml
zKVE%)f5?8N-y^kehmPA<M|m_q{C3RV+O_bO@8W~@doqmMtha2n=MHWBlhV1){-&~#
MNASmW_9aPr0BVhrg8%>k

literal 0
HcmV?d00001

diff --git a/timeside/analyzer/protoStart3.dat b/timeside/analyzer/protoStart3.dat
new file mode 100644
index 0000000000000000000000000000000000000000..718c07d9e68be9bc51663de33d46e47bb69a372b
GIT binary patch
literal 329
zcmZo*O3o|IEvVE>&M!*U%Pq|*$xJLNO049HFG@|$&nqq|DorloDrAJH;>t^b$QCkr
zGqi>>Cbb6@GHZA<dP}xK6{M6@7Nl|&vV=0FS$H#eGXfQ`YIrk;GTQk0`FZ^Z0x;pt
zP?FRcdctL0nV`$Ynf8zOe$RP3f1!QEk6Go`{7dZp_x#pPc)8eq`ClP}LXma$mHU=I
zG+zD6e$So~zf}|7+cSW{2m9ct4YB-PckLx=vZj7NxYz!<y)h%R_a6HTRwb(@f81ej
z#5ZZx;@v0gxy7$7WskXN@0jdte&yu_dn0-Cq_tm;+MgC<aE!jN-rmG><JRi@7510b
zb67XYFSd_-YgRht-#q(`dlFYKeLu(EvpGGAVd;GP@0#4@tREKIZ|AsIddYaMz393Z
Nzin7%*_R~g0RU<Xjd1_~

literal 0
HcmV?d00001

-- 
2.39.5