Speaker Recognition: GMM-UBM

1. WHY --- 为什么需要使用GMM-UBM来建立Individual Speaker Modeling？

"Usually, we do not have much data from a single speaker. In most practical cases related to text-independent scenarios, the enrollment data is at best in the order of a minute." “Assuming that the number of Gaussians used in the mixture mode, Γ ∼100,
then it is easy to understand why there is no where close to enough data to be able to estimate the mixture parameters for the speaker.”  

 

2. WHAT --- UBM模型和Individual Speaker Modeling长什么样？

- the GMM are usually diagonal.

- Practice has shown that it is advantageous to train two separate background models, one for female and the other one for          male speakers.

- the number of Gaussians used in a UBM是多少?

 

3. HOW --- 怎么基于UBM模型来建立Individual Speaker Modeling？

- 调整什么参数？

 Only means adapted  或者  All parameters adapted

- 用什么方法调整？

通常是MAP方法，“For very short enrollment utterances (a few seconds), some other methods have shown to be more effective. Maximum likelihood linear regression (MLLR) ”

 

4. Advanced Topic

- 怎么减少GMM-UBM的computationally intensive

- 怎么解决GMM-UBM的phonetic mismatch problem

 

参考：

[1] An Overview of Text-Independent Speaker Recognition: from Features to Supervectors