shithub: opus

Info  •  Files  •  Log  •  Branches

Adding pitch

--- a/dnn/denoise.c

+++ b/dnn/denoise.c

@@ -46,7 +46,7 @@

 #define WINDOW_SIZE (2*FRAME_SIZE)

 #define FREQ_SIZE (FRAME_SIZE + 1)

-#define PITCH_MIN_PERIOD 20

+#define PITCH_MIN_PERIOD 32

 #define PITCH_MAX_PERIOD 256

 #define PITCH_FRAME_SIZE 320

 #define PITCH_BUF_SIZE (PITCH_MAX_PERIOD+PITCH_FRAME_SIZE)

@@ -321,7 +321,7 @@

     float g_1;

     _celt_autocorr(x, ac, NULL, 0, LPC_ORDER, WINDOW_SIZE);

     /* -40 dB noise floor. */

-    ac[0] += ac[0]*1e-4;

+    ac[0] += ac[0]*1e-4 + 320/12;

     /* Lag windowing. */

     for (i=1;i<LPC_ORDER+1;i++) ac[i] *= (1 - 6e-5*i*i);

     e = _celt_lpc(lpc, rc, ac, LPC_ORDER);

@@ -582,7 +582,6 @@

     preemphasis(x, &mem_preemph, x, PREEMPHASIS, FRAME_SIZE);

     compute_frame_features(st, iexc, X, P, Ex, Ep, Exp, features, x);

-    pitch_filter(X, P, Ex, Ep, Exp, g);

 #if 1

     fwrite(features, sizeof(float), NB_FEATURES, stdout);

     fwrite(iexc, sizeof(signed char), FRAME_SIZE, fexc);

--- a/dnn/lpcnet.py

+++ b/dnn/lpcnet.py

@@ -16,7 +16,7 @@

 def new_wavernn_model():

-    pcm = Input(shape=(None, 1))

+    pcm = Input(shape=(None, 2))

     feat = Input(shape=(None, nb_used_features))

     rep = Lambda(lambda x: K.repeat_elements(x, 160, 1))

--- a/dnn/train_lpcnet.py

+++ b/dnn/train_lpcnet.py

@@ -7,6 +7,7 @@

 from keras.callbacks import ModelCheckpoint

 from ulaw import ulaw2lin, lin2ulaw

 import keras.backend as K

+import h5py

 import tensorflow as tf

 from keras.backend.tensorflow_backend import set_session

@@ -23,10 +24,11 @@

 pcmfile = sys.argv[1]

 feature_file = sys.argv[2]

+frame_size = 160

 nb_features = 54

 nb_used_features = lpcnet.nb_used_features

 feature_chunk_size = 15

-pcm_chunk_size = 160*feature_chunk_size

+pcm_chunk_size = frame_size*feature_chunk_size

 data = np.fromfile(pcmfile, dtype='int8')

 nb_frames = len(data)//pcm_chunk_size

@@ -38,6 +40,15 @@

 in_data = np.concatenate([data[0:1], data[:-1]])/16.;

+features = np.reshape(features, (nb_frames*feature_chunk_size, nb_features))

+pitch = 1.*data

+pitch[:320] = 0

+for i in range(2, nb_frames*feature_chunk_size):

+    period = int(50*features[i,36]+100)

+    period = period - 4

+    pitch[i*frame_size:(i+1)*frame_size] = data[i*frame_size-period:(i+1)*frame_size-period]

+in_pitch = np.reshape(pitch/16., (nb_frames, pcm_chunk_size, 1))

+

 in_data = np.reshape(in_data, (nb_frames, pcm_chunk_size, 1))

 out_data = np.reshape(data, (nb_frames, pcm_chunk_size, 1))

 out_data = (out_data.astype('int16')+128).astype('uint8')

@@ -44,7 +55,14 @@

 features = np.reshape(features, (nb_frames, feature_chunk_size, nb_features))

 features = features[:, :, :nb_used_features]

-checkpoint = ModelCheckpoint('lpcnet1c_{epoch:02d}.h5')

+

+in_data = np.concatenate([in_data, in_pitch], axis=-1)

+

+#with h5py.File('in_data.h5', 'w') as f:

+# f.create_dataset('data', data=in_data[:50000, :, :])

+# f.create_dataset('feat', data=features[:50000, :, :])

+

+checkpoint = ModelCheckpoint('lpcnet1e_{epoch:02d}.h5')

 #model.load_weights('wavernn1c_01.h5')

 model.compile(optimizer=Adam(0.002, amsgrad=True, decay=2e-4), loss='sparse_categorical_crossentropy', metrics=['sparse_categorical_accuracy'])

-- 

⑨