inter class mllr for speaker adaptation
DESCRIPTION
Inter Class MLLR for Speaker Adaptation. Presenter : 陳彥達. Reference. Sam-Joo Doh and Richard M. Stern, “Inter-Class MLLR for Speaker Adaptation”, ICASSP 2000. Outline. Introduction Concept of inter-class MLLR Inter-class function training Experiments. Introduction. - PowerPoint PPT PresentationTRANSCRIPT
Inter Class MLLR for Speaker Adaptation
Presenter : 陳彥達
Reference
Sam-Joo Doh and Richard M. Stern, “Inter-Class MLLR for Speaker Adaptation”, ICASSP 2000.
Outline Introduction Concept of inter-class MLLR Inter-class function training Experiments
Introduction Why do we use MLLR ?
Simple idea Few unknown parameters Sparse adaptation data Rapid adaptation
Introduction(2)
i all Gaussian
,
i Class 1
,
i Class 2
)(ˆ if
)(ˆ 1 ii f
)(ˆ 2 ii f
Introduction(3) Single-class MLLR
All parameters use the same transformation in adaptation
More reliable for small amount of adaptation data
Multi-class MLLR Parameters in different classes use different
transformation in adaptation More reliable for large amount of adaptation
data
Introduction(4) Shortcoming of conventional MLLR
The number of classes should be carried out according to the amount of adaptation data.
Classes are independent in multi-class MLLR, so some parameters may not be adapted.
Main idea of inter-class MLLR Use correlation between different classes to
compensate for the shortcoming mentioned above.
Concept of inter-class MLLR Inter-class function
The relation between different classes
if is the inter-class function between class 1 and class 2
, i class 1
,
i class 2
)(12 g
)())(()(ˆ )12(11212 iiii fgff
)(ˆ 1 ii f
Concept of inter-class MLLR(2) Model setup steps
Define multiple classes ( say class 1~ n ) Find inter-class functions between each class
Adaptation steps Choose a target class which is going to be
adapted ( say class k ) Rank other classes according to their
“closeness” to the target class
Concept of inter-class MLLR(3) If adaptation data ( i target class k )
coming, use conventional MLLR to find If adaptation data ( i target class k )
coming, use inter-class function to convert as the adaptation data in class k, and then use conventional MLLR to find
Repeat above steps until all classes are adapted
i )(kf
i i
)(kf
Concept of inter-class MLLR(4) Adaptation data are selected from classes of
decreasing proximity to the target class until there are sufficient data to estimate the target function.
Limit cases no neighboring classes used → conventional
multi-class MLLR All neighboring classes used → conventional
single-class MLLR
Inter-class function training ,
i class m
, i class n
let
then
, i class n
mnimnimn dTg )(
mimimi bAf )(ˆ
ninini bAf )(ˆ
mmnimnm
mimnmimnmi
bdTA
bgAgf
)(
)())((ˆ
Inter-class function training(2)Assuming we have training data of R speakers. We use these data to train , for each class for each speaker.
ie. s={1,2,…,R}, m={1,2,…,n}.
,
i class n, for class m for speaker smsmnimnms
si bdTA ,,
)( )(ˆ
),( ,, msms bA
∴
mnimnms
si dTbA
ms )ˆ( ,
)(1
,
Inter-class function training(3)
Let
we use the equation above and training data for all speakers to obtain and by conventional MLLR.
)ˆ(ˆ ,)(1),(
, mss
ims
i bAms
mnimnms
i dT ),(ˆ
mnT mnd
Experiments Mean-square error from simulated estimates of G
aussian means
Experiments(2) Word error rate for different types of MLLR
25 training speakers 13 phonetic-based regression classes 10 testing speakers, 20 sentences per speaker
for testing, 5 sentences per speaker for adaptation
use all the neighbor classes to estimate each target class
Silence and noise phones are not adapted
Experiments(3)