How to add my voice samples to validation.txt and testing.txt? Speech recognition

2 次查看（过去 30 天）
N/A
N/A 2020-1-6
编辑： N/A 2020-1-6
Hi im trying to do my own project with matlab basic on this example:https://www.mathworks.com/help/deeplearning/examples/deep-learning-speech-recognition.html
i dont know how to divide my own samples to validation.txt and testing.txt just write it?
When i try write it by myself in part Split Data into Training, Validation, and Test Sets, when i try in matlab this :
XTrain = speechSpectrograms(adsTrain,segmentDuration,frameDuration,hopDuration,numBands);
XTrain = log10(XTrain + epsil);
XValidation = speechSpectrograms(adsValidation,segmentDuration,frameDuration,hopDuration,numBands);
XValidation = log10(XValidation + epsil);
XTest = speechSpectrograms(adsTest,segmentDuration,frameDuration,hopDuration,numBands);
XTest = log10(XTest + epsil);
YTrain = adsTrain.Labels;
YValidation = adsValidation.Labels;
YTest = adsTest.Labels;
it gives me error :
Index in position 2 is invalid. Array indices must be positive integers
or logical values.
Error in speechSpectrograms (line 43)
X(:,ind,1,i) = spec;
I dont know how to fix it, my own data set is 14 wav files : MONO 16000Hz 16 bits PCM Windows created by using Audacity 2.2.2
Matlab 2019
it is that because I divide all 14 wav files in this two txt files?
when i try to write only 5 wav files do each txt files it gives me the same error and 4 were not saved anywhere i wantem them to go to training but i dont know how to split them to this to txt files.
Do i have to ender this wav's manually or divide using matlab or something? in this example theres no anwser how to split them.

请先登录，再回答此问题。

回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Speech Recognition 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by