def __init__(
self,
bidim,
btype: str = "blstmp",
blayers: int = 3,
bunits: int = 300,
bprojs: int = 320,
num_spk: int = 1,
use_noise_mask: bool = True,
dropout_rate: float = 0.0,
badim: int = 320,
ref_channel: int = -1,
beamformer_type: str = "mvdr",
eps: float = 1e-6,
# only for WPD beamformer
btaps: int = 5,
bdelay: int = 3,
):
super().__init__()
bnmask = num_spk + 1 if use_noise_mask else num_spk
self.mask = MaskEstimator(btype,
bidim,
blayers,
bunits,
bprojs,
dropout_rate,
nmask=bnmask)
self.ref = AttentionReference(bidim,
badim) if ref_channel < 0 else None
self.ref_channel = ref_channel
self.use_noise_mask = use_noise_mask
assert num_spk >= 1, num_spk
self.num_spk = num_spk
self.nmask = bnmask
if beamformer_type not in ("mvdr", "mpdr", "wpd"):
raise ValueError(
"Not supporting beamformer_type={}".format(beamformer_type))
if beamformer_type == "mvdr" and (not use_noise_mask):
if num_spk == 1:
logging.warning(
"Initializing MVDR beamformer without noise mask "
"estimator (single-speaker case)")
logging.warning(
"(1 - speech_mask) will be used for estimating noise "
"PSD in MVDR beamformer!")
else:
logging.warning(
"Initializing MVDR beamformer without noise mask "
"estimator (multi-speaker case)")
logging.warning(
"Interference speech masks will be used for estimating "
"noise PSD in MVDR beamformer!")
self.beamformer_type = beamformer_type
assert btaps >= 0 and bdelay >= 0, (btaps, bdelay)
self.btaps = btaps
self.bdelay = bdelay if self.btaps > 0 else 1
self.eps = eps
def __init__(self,
bidim,
btype='blstmp',
blayers=3,
bunits=300,
bprojs=320,
bnmask=2,
dropout_rate=0.0,
badim=320,
ref_channel: int = -1,
beamformer_type='mvdr'):
super().__init__()
self.mask = MaskEstimator(btype,
bidim,
blayers,
bunits,
bprojs,
dropout_rate,
nmask=bnmask)
self.ref = AttentionReference(bidim, badim)
self.ref_channel = ref_channel
self.nmask = bnmask
if beamformer_type != 'mvdr':
raise ValueError(
'Not supporting beamformer_type={}'.format(beamformer_type))
self.beamformer_type = beamformer_type
def __init__(
self,
wtype: str = 'blstmp',
widim: int = 257,
wlayers: int = 3,
wunits: int = 300,
wprojs: int = 320,
dropout_rate: float = 0.0,
taps: int = 5,
delay: int = 3,
use_dnn_mask: bool = True,
iterations: int = 1,
normalization: bool = False,
):
super().__init__()
self.iterations = iterations
self.taps = taps
self.delay = delay
self.normalization = normalization
self.use_dnn_mask = use_dnn_mask
self.inverse_power = True
if self.use_dnn_mask:
self.mask_est = MaskEstimator(wtype,
widim,
wlayers,
wunits,
wprojs,
dropout_rate,
nmask=1)