Hello.
I am currently developing a new speech coder for application to the HTS.
In distributed version of HTS, features of the speech have defined by STRAIGHT with 39th spectrum, 5th BAP and F0.
(Total 45*3 due to their delta and delta-delta, as far as I know)
I wonder when I apply different speech coder having different feature _expression_, are there any limitations in HTS?
(Feature size, number of feature type, features data type….)
Regards.
-Kwang Myung
---------------------------------------------------------------------------------------------
KwangMyung Jeon (Ph.D. Student)
Human Computing Laboratory
School of Information and Communications
Gwangju Institute of Science and Technology 1 Oryong-dong, Buk-gu Gwangju 500-712, SOUTH KOREA
Tel) +82-62-970-3121
Fax) +82-62-970-2204
Email) kmjeon@xxxxxxxxxx
---------------------------------------------------------------------------------------------