- https://www.rug.nl/staff/a.kunikoshi/research
- Joined on
2017-03-08
Block a user
97486e5599
dataset for experiments in check_novoapi is updated.
2004399179
novoapi_functions.py is adjusted to use convert_phoneset.py.
b444b70af9
fame_phonetics.py and functions to make quests.hed to tie triphone are added.
bf586fcde5
triphone training is added.
fdd165ce6a
re-aligned mlf file include less files than original mlf file. Therefore the scp file should also be updated accordingly, when re-estimation is performed. this bug is fixed.
8f89f60538
dataset is made.
f6e563ecd3
moved testing parts in htk_vs_kaldi into stimmen_test.py
da0242b0e1
make sure all the phones in stimmen transcription can be treated correctly.
f6e7c8eefa
bug related encoding on label file is fixed.
322a8a0079
label files are extracted. hcompv_scp is made.
22cccfb61d
fix the bug there are characters in the lexicon which cannot be described in ascii.
dc6b7b84b6
lexicon is made.
8cda93de75
fame_asr phoneset is added including reduced version and htk compatible version.
87abbbb95a
correspondence between lex.asr and lex.ipa is automatically obtained. header is added to the functions in fame_functions.py.
813f013d7a
phonset is given as fame_phoneset.py. translation key is obtained based on the information.
7844a56281
HTK related functions are moved to pyhtk project. fame acoustic models are made using fame_hmm.py. feature extraction is completed. A function is being made to get translation key from ipa to asr.
24ac56ac0e
to transfer working environment to McRoberts laptop.
82a8e2302f
rozen-test is added.
de5c9cecb9
The bug regarding novoapi for Python 3.6 is solved. The detail can be found in novoapi_for_python3x/readme.txt
8efb091715
confusion matrix is output.
05e8a671c1
forced alignment by novoapi is performed.
1622655542
functions are added to perform forced_alignment using novoapi. results can be written in novo70 or IPA.
d6d5543d03
novoapi_functions is added to novo70 specific functions.
d6e005b1cb
find pronunciation variants which all phones are in novo70.
dd9e3d820b
started to check which words in stimmen transcription consists of only phones in novo70 phoneset.
a77ed9d4dd
resolve the conflicts.
df046ffc26
forced_alignment_novo.py is removed (.gitignore). commit history is cleaned up.
beff33fdf9
revert "load novo phoneset" to continue working.
af785e51cf
commit to clean up