| File name | H1 help | File size |
|---|---|---|
| addMyPath.m | 187 Bytes | |
| getExePerf.m | speakerIdentify: speaker identification using GMM parameters | 1787 Bytes |
| go.m | Main program for speaker identification | 1092 Bytes |
| goCheckEpd.m | out=epdByVol(y, fs, nbits, epdParam, plotOpt); | 495 Bytes |
| goDebug.m | Evaluate utterance-based recognition rate for speaker identification | 485 Bytes |
| goFrameRrWrtGaussianNum.m | Compute frame-based recognition rates with varying number of Gaussian components | 1752 Bytes |
| goMergeTrain.m | Merge two speakerSet to get recog. rate of speaker identification | 1999 Bytes |
| goPlotHist.m | 714 Bytes | |
| goSegmentRr.m | Compute segment recognition rate w.r.t. varying segment sizes | 947 Bytes |
| goSpeakerIdByDtw.m | Main program for speaker identification by DTW | 2603 Bytes |
| goSpeakerVerify.m | fprintf('%d/%d\n', i, speakerNum); | 2526 Bytes |
| goTest.m | load temp1.txt | 804 Bytes |
| goTrainGmm.m | Train GMM for speaker identification | 1795 Bytes |
| goTrainGmm4speakerVerification.m | Train GMM for speaker verification using speaker models and anti-speaker models | 2487 Bytes |
| goTutorial.m | % Tutorial on text-dependent speaker recognition | 3686 Bytes |
| goUtterRr.m | Evaluate utterance-based recognition rate for speaker identification | 1153 Bytes |
| goUtterRrOutsideTest.m | Evaluate utterance-based recognition rate for speaker identification | 1654 Bytes |
| goUtterRrViaExe.m | Evaluate utterance-based recognition rate for speaker identification | 1497 Bytes |
| goUtterRrWrtGaussianNum.m | Compute the utterance-based recognition rates for speaker identification. | 2618 Bytes |
| listPersonRr.m | 372 Bytes | |
| sidFeaExtract.m | Feature extraction for speaker identification | 4258 Bytes |
| sidOptSet.m | sidOptSet: Set parameters for speaker identification/verification | 3033 Bytes |
| sidPerfEval.m | Performance evaluation of speaker identification | 3254 Bytes |
| speakerIdDtw.m | Speaker ID using DTW | 1950 Bytes |
| speakerSet2ds.m | speakerSet2ds: Transform speakerSet to DS | 447 Bytes |
| speakerSetAddFea.m | ====== Feature extraction | 1211 Bytes |
| speakerSetFeaTransform.m | 229 Bytes | |
| speakerSetMerge.m | speakerSetMerge: Merge two speakerSet | 543 Bytes |
| speakerSetWrite.m | 801 Bytes | |
| ttt.m | Compute the mean volume, clarity, and pitch | 868 Bytes |
| wave2fea.m | wave2fea: Audio file to feature | 3487 Bytes |
| wave2mfccInt.m | wave2mfccInt: Fixed-point MFCC computation by calling an external executable | 644 Bytes |