def get_phoneme_mapping(iphn, phn2int, n_taken=0):
# Reverse the codebook for easier manipulation
int2phn = flip(phn2int)
# Define a sub-dictionary of the picked phonemes
class2phn = {j + n_taken: int2phn[i] for j, i in enumerate(iphn)}
class2int = {j + n_taken: i for j, i in enumerate(iphn)}
return class2phn, class2int
def prepare_data(fname_dtest=None,
classmap_existing=None,
fname_dtrain=None,
n_phn=None,
totclasses=None,
verbose=False):
# Read the datafiles
te_DATA, te_keys, te_lengths, phn2int_61, te_PHN = pkl.load(
open(fname_dtest, "rb"))
tr_DATA, tr_keys, tr_lengths, tr_PHN = pkl.load(open(fname_dtrain, "rb"))
if verbose:
print("Data loaded from files.")
# Take labels down to phoneme level
data_tr, label_tr = to_phoneme_level(tr_DATA)
data_te, label_te = to_phoneme_level(te_DATA)
# Checkout table 3 at
# https://www.intechopen.com/books/speech-technologies/phoneme-recognition-on-the-timit-database
# Or in the html file
# for details
phn2int = phn2int_61
if totclasses == 39:
f = partial(phn61_to_phn39,
int2phn_61=flip(phn2int_61),
data_folder=os.path.dirname(fname_dtest))
label_tr, phn2int_39 = f(label_tr)
label_te, _ = f(label_te, phn2int_39=phn2int_39)
data_tr, label_tr = remove_label(data_tr, label_tr, phn2int_39)
data_te, label_te = remove_label(data_te, label_te, phn2int_39)
phn2int_39.pop('-', None)
phn2int = phn2int_39
# List the phoneme names already in the data folder.
taken = [v for k, v in classmap_existing.items()]
# Deduce the available phonemes
available_phn = [v for k, v in phn2int.items() if not k in taken]
# Pick new random phonemes
iphn = np.random.permutation(available_phn)[:n_phn]
# Find the phonemes in the dataset
xtrain, ytrain = getsubset(data_tr, label_tr, iphn)
xtest, ytest = getsubset(data_te, label_te, iphn)
class2phn, class2int = get_phoneme_mapping(iphn,
phn2int,
n_taken=len(taken))
return xtrain, ytrain, xtest, ytest, class2phn, class2int
def get_phoneme_mapping(iphn, phn2int, n_taken=0):
"""
This function takes an array of ints 'iphn' and a mapping dictionary 'phn2int'
----
Args:
- iphn: List of integers that denote the class number which the phoneme is associated with
- phn2int: Dictionary describing the mapping from phones (phn) to integers (int) (sort of a codebook)
- n_taken: Possible number of classses already processed
Outputs:
- class2phn: A subdictionary that denotes the new subclass number and the corresponding phoneme associated for that subclass
- class2phn: A subdictionary that denotes the new subclass number and the corresponding original class no. associated for that subclass
"""
# Reverse the codebook for easier manipulation
int2phn = flip(phn2int)
# Define a sub-dictionary of the picked phonemes
class2phn = {j + n_taken: int2phn[i] for j, i in enumerate(iphn)}
class2int = {j + n_taken: i for j, i in enumerate(iphn)}
return class2phn, class2int
os.path.basename(fname_dtest))
fname_dtrain = os.path.join(os.path.dirname(fname_dtest),
"train.{}.pkl".format(nfeats))
cmap = read_classmap(os.path.dirname(args.classmap))
te_DATA, te_keys, te_lengths, phn2int_61, te_PHN = pkl.load(
open(fname_dtest, "rb"))
tr_DATA, tr_keys, tr_lengths, tr_PHN = pkl.load(open(fname_dtrain, "rb"))
data_te, label_te = to_phoneme_level(te_DATA)
data_tr, label_tr = to_phoneme_level(tr_DATA)
phn2int = phn2int_61
if args.totclass == 39:
f = partial(phn61_to_phn39,
int2phn_61=flip(phn2int_61),
data_folder=os.path.dirname(fname_dtest))
label_tr, phn2int_39 = f(label_tr)
label_te, _ = f(label_te, phn2int_39=phn2int_39)
data_te, label_te = remove_label(data_te, label_te, phn2int_39)
data_te, label_te = remove_label(data_te, label_te, phn2int_39)
phn2int_39.pop('-', None)
phn2int = phn2int_39
iphn = [phn2int[v] for k, v in cmap.items()]
xtrain, ytrain = getsubset(data_tr, label_tr, iphn)
xtest, ytest = getsubset(data_te, label_te, iphn)
xtrain, xtest = normalize(xtrain, xtest)
args = parser.parse_args()
fname_dtest = args.input
mode, nfeats, ntype, snr = parse("{}.{}.{}.{:d}db.pkl", os.path.basename(fname_dtest))
fname_dtrain = os.path.join(os.path.dirname(fname_dtest), "train.{}.pkl".format(nfeats))
cmap = read_classmap(os.path.dirname(args.classmap))
te_DATA, te_keys, te_lengths, phn2int_61, te_PHN = pkl.load(open(fname_dtest, "rb"))
tr_DATA, tr_keys, tr_lengths, tr_PHN = pkl.load(open(fname_dtrain, "rb"))
data_te, label_te = to_phoneme_level(te_DATA)
data_tr, label_tr = to_phoneme_level(tr_DATA)
phn2int = phn2int_61
if args.totclass == 39:
f = partial(phn61_to_phn39, int2phn_61=flip(phn2int_61), data_folder=os.path.dirname(fname_dtest))
label_tr, phn2int_39 = f(label_tr)
label_te, _ = f(label_te, phn2int_39=phn2int_39)
data_te, label_te = remove_label(data_te, label_te, phn2int_39)
data_te, label_te = remove_label(data_te, label_te, phn2int_39)
phn2int_39.pop('-', None)
phn2int = phn2int_39
iphn = [phn2int[v] for k, v in cmap.items()]
xtrain, ytrain = getsubset(data_tr, label_tr, iphn)
xtest, ytest = getsubset(data_te, label_te, iphn)
xtrain, xtest = normalize(xtrain, xtest)
def prepare_data(fname_dtest=None,
classmap_existing=None,
fname_dtrain=None,
n_phn=None,
totclasses=None,
verbose=False):
"""
This is the function taht is repsonsible for reading the data files, both (training and test data in .pkl format)
and partitions the .pkl files on a per phoneme basis or a per class basis (because the task is Phone Recognition)
----
Args:
- fname_dtest: full path of the test data file containing data and labels in .pkl format
- fname_dtrain: full path of the training data file containing data and labels in .pkl format
- classmap_existing: full path for the existing classmap dictionary file if present
- n_phn: No. of phonemes considered for partition of left to be retrieved
- totclasses: Total number of phonemes considered in the list
- verbose: Flag for controlling verbose output
Output:
- xtrain: Training data for the subclassed dataset
- ytrain: Training data label for the subclassed dataset
- xtrain: Training data for the subclassed dataset
- ytrain: Training data label for the subclassed dataset
- class2phn: A subdictionary that denotes the new subclass number and the corresponding phoneme associated for
that subclass
- class2int: A subdictionary that denotes the new subclass number and the corresponding original class no. associated
for that subclass
"""
# Read the datafiles
te_DATA, te_keys, te_lengths, phn2int_61, te_PHN = pkl.load(
open(fname_dtest, "rb"))
tr_DATA, tr_keys, tr_lengths, tr_PHN = pkl.load(open(fname_dtrain, "rb"))
if verbose:
print("Data loaded from files.")
# Take labels down to phoneme level
data_tr, label_tr = to_phoneme_level(tr_DATA)
data_te, label_te = to_phoneme_level(te_DATA)
# Checkout table 3 at
# https://www.intechopen.com/books/speech-technologies/phoneme-recognition-on-the-timit-database
# Or in the html file
# for details
phn2int = phn2int_61
if totclasses == 39:
f = partial(phn61_to_phn39,
int2phn_61=flip(phn2int_61),
data_folder=os.path.dirname(fname_dtest))
label_tr, phn2int_39 = f(label_tr)
label_te, _ = f(label_te, phn2int_39=phn2int_39)
data_tr, label_tr = remove_label(data_tr, label_tr, phn2int_39)
data_te, label_te = remove_label(data_te, label_te, phn2int_39)
phn2int_39.pop('-', None)
phn2int = phn2int_39
# List the phoneme names already in the data folder.
taken = [v for k, v in classmap_existing.items()]
# Deduce the available phonemes
available_phn = [v for k, v in phn2int.items() if not k in taken]
# Pick new random phonemes
iphn = np.random.permutation(available_phn)[:n_phn]
# Find the phonemes in the dataset
xtrain, ytrain = getsubset(data_tr, label_tr, iphn)
xtest, ytest = getsubset(data_te, label_te, iphn)
class2phn, class2int = get_phoneme_mapping(iphn,
phn2int,
n_taken=len(taken))
return xtrain, ytrain, xtest, ytest, class2phn, class2int