VoxForge
Hi, all,
When people talked about the WSJ database, they always mentioned concepts of development set (DEV), and evaluation set (EVAL). Can anyone tell me what a DEV is, and what is it used for?
Thank you so much.
Mike
--- (Edited on 2/9/2015 4:08 pm [GMT-0600] by weedwind) ---
There are hyperparameters used in decoding (language weight, word insertion probability, decoding beams).
Development set is used to estimate best possible hyperparameters.
The final result is verified on a test set.
You can read more about development set or, another name, validation set here:
--- (Edited on 2/10/2015 01:21 [GMT+0300] by nsh) ---
Thank you so much for your answer. I read through that reference, but I still want to make it totally clear. So, let me ask a specific question.
Suppose I have a MFCC frontend for an ASR task. I want to tune the number of filters in the filterbank (though people know a good number, but just assume it's unknown). I have a training set, a validation set, and a test set, can you please show me how I should proceed?
Mike
--- (Edited on 2/9/2015 6:06 pm [GMT-0600] by weedwind) ---
Also, why some database have a validation set, such as WSJ, but some do not, such as TIMIT?
--- (Edited on 2/9/2015 6:13 pm [GMT-0600] by weedwind) ---
> Suppose I have a MFCC frontend for an ASR task. I want to tune the number of filters in the filterbank (though people know a good number, but just assume it's unknown). I have a training set, a validation set, and a test set, can you please show me how I should proceed?
> Also, why some database have a validation set, such as WSJ, but some do not, such as TIMIT?
--- (Edited on 2/11/2015 13:01 [GMT+0300] by nsh) ---