Speech Recognition using MFCC and k-NN algorithm in Matlab

2 次查看(过去 30 天)
I am working on speech recognition and I have 30 recordings for 5 spoken words from 5 different speakers. I have extracted the features using MFCC algorithm. Now I have the following questions:
  1. Do I have to save these features in .mat file? Would that be in a single file? Because different samples may not have the same number of rows.
  2. How to feed these into fitcknn() function in matlab? I looked through the documentation but still I am not clear on how to apply this to my data.
Thanks in advance.

回答(1 个)

Walter Roberson
Walter Roberson 2017-8-10
You can save them all in one .mat file if you save them as different variables, or if you save them all inside one cell array.
  2 个评论
KS
KS 2017-8-11
编辑:KS 2017-8-11
Thank you Walter for your answer. But what about the second part of my question? How do I use that function? Any ideas?
Walter Roberson
Walter Roberson 2017-8-11
The examples on the documentation page show how to use it. However, I do not know anything about why to use it.

请先登录,再进行评论。

类别

Help CenterFile Exchange 中查找有关 Speech Recognition 的更多信息

Community Treasure Hunt

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

Start Hunting!

Translated by