Mercurial > hg > emotion-detection-top-level
comparison Code/Descriptors/Matlab/Common/detect_VoicedUnvoiced.m @ 4:92ca03a8fa99 tip
Update to ICASSP 2013 benchmark
author | Dawn Black |
---|---|
date | Wed, 13 Feb 2013 11:02:39 +0000 |
parents | a3d62264030c |
children |
comparison
equal
deleted
inserted
replaced
3:e1cfa7765647 | 4:92ca03a8fa99 |
---|---|
8 %---------------- GET THE SILENT FRAME VALUES ------------------- | 8 %---------------- GET THE SILENT FRAME VALUES ------------------- |
9 | 9 |
10 % only wish to consider pitch values from voiced frames. | 10 % only wish to consider pitch values from voiced frames. |
11 % silent and unvoiced frames will produce pitch values that | 11 % silent and unvoiced frames will produce pitch values that |
12 % are random and therefore will bias our results | 12 % are random and therefore will bias our results |
13 segmentFrames = detect_Silence( sampleFileName, 0 ); | 13 segmentFrames = detect_Silence( [sampleFileName '.wav'], 0 ); |
14 | 14 |
15 % remove the silent frames | 15 % remove the silent frames |
16 [x, fs, frameLength, noOfFrames] = openFile( [ sampleFileName '.wav' ] ); | 16 [x, fs, frameLength, noOfFrames] = openFile( [ sampleFileName '.wav' ] ); |
17 [ silentFrames ] = removeSilentData( segmentFrames, noOfFrames ); | 17 [ silentFrames ] = getSilentDataArray( segmentFrames, noOfFrames ); |
18 | 18 |
19 % [vuv] = voicingByClustering( nonSilentAudio, fs, noOfFrames, frameLength ); | 19 % [vuv] = voicingByClustering( nonSilentAudio, fs, noOfFrames, frameLength ); |
20 [vuv] = calculate_VoicedUnvoicedDecision( sampleFileName, x, fs, frameLength, noOfFrames, silentFrames ); | 20 [vuv] = calculate_VoicedUnvoicedDecision( sampleFileName, x, fs, frameLength, noOfFrames, silentFrames ); |
21 | 21 |
22 noOfValidFrames = length(vuv); | 22 noOfValidFrames = length(vuv); |