This chapter describes the linguistic resources included in the file
ben.zip of the
"Ortolang repository".
List of phonemes
Consonant Plosives
SPPAS
IPA
Description
Examples
b
b
voiced bilabial
b_h
bʰ
voiced bilabial aspirated
c
c
voiceless palatal
c_h
cʰ
voiceless palatal aspirated
d
d
voiced alveolar
d_h
dʰ
voiced alveolar aspirated
d| ɖ | voiced retroflex | | | d_h
ɖʰ
voiced retroflex aspirated
g
g
voiced velar
g_h
gʰ
voiced velar
J\
ɟ
voiced palatal
J_h
ɟʰ
voiced palatal aspirated
k
k
voiceless velar
k_h
kʰ
voiceless velar aspirated
p
p
voiceless bilabial
p_h
pʰ
voiceless bilabial aspirated
t
t
voiceless alveolar
t_h
tʰ
voiceless alveolar aspirated
t`
ʈ
voiceless retroflex
t`_h
ʈʰ
voiceless retroflex aspirated
Notice that J and J_h were both in the first version of the
pronunciation dictionary but are no longer in the current version. They
remain in the acoustic model, so they can be used for Phonetization.
The phonemes have been converted to X-SAMPA and the file format to
HTK-ASCII by Brigitte Bigi. Pronunciations were revised by Moumita
PAKRASHI of Centre for Linguistic Science and Technology, Indian
Institute of Technology Guwahati.
The dictionary is re-distributed under the terms of its original
Creative Commons Attribution-NonCommercial-ShareAlike 4.0
International Public License.
Acoustic Model
The model was developed using a Python script available in the SPPAS package:
acmtrain.py.
This is the second version of the acoustic model. It was trained with
a set of 6 manually time-aligned files (totalling about 18 seconds of
speech) and 1,300 orthographically transcribed files (totalling 36
minutes of speech).
The model is distributed under the terms of the Creative Commons
Attribution-NonCommercial-ShareAlike 4.0 International Public
License.