bob.machine.JFAMachine¶
-
class
bob.machine.JFAMachine((object)self, (JFABase)jfa_base) → None :¶ Bases:
bob.machine._machine.MachineGMMStatsScalarBaseA JFAMachine. An attached JFABase should be provided for Joint Factor Analysis. The JFAMachine carries information about the speaker factors y and z, whereas a JFABase carries information about the matrices U, V and D.
References: [1] ‘Explicit Modelling of Session Variability for Speaker Verification’, R. Vogt, S. Sridharan, Computer Speech & Language, 2008, vol. 22, no. 1, pp. 17-38 [2] ‘Session Variability Modelling for Face Authentication’, C. McCool, R. Wallace, M. McLaren, L. El Shafey, S. Marcel, IET Biometrics, 2013
Builds a new JFAMachine.
- __init__( (object)self) -> None :
- Constructs a 1x1 JFAMachine instance. You have to set a JFABase afterwards.
- __init__( (object)self, (HDF5File)config) -> None :
- Constructs a new JFAMachine from a configuration file.
- __init__( (object)self, (JFAMachine)machine) -> None :
- Copy constructs a JFAMachine
-
__init__((object)self, (JFABase)jfa_base) → None :¶ Builds a new JFAMachine.
- __init__( (object)self) -> None :
- Constructs a 1x1 JFAMachine instance. You have to set a JFABase afterwards.
- __init__( (object)self, (HDF5File)config) -> None :
- Constructs a new JFAMachine from a configuration file.
- __init__( (object)self, (JFAMachine)machine) -> None :
- Copy constructs a JFAMachine
Methods
__init__((object)self, (JFABase)jfa_base)Builds a new JFAMachine. estimate_ux((JFAMachine)self, …)Estimates Ux (LPT assumption) given GMM statistics. estimate_x((JFAMachine)self, …)Estimates the session offset x (LPT assumption) given GMM statistics. forward((MachineGMMStatsScalarBase)self, …)Executes the machine on the GMMStats, and returns the (scalar) output. forward_((MachineGMMStatsScalarBase)self, …)Executes the machine on the GMMStats, and returns the (scalar) output. forward_ux((JFAMachine)self, …)Processes the GMM statistics and Ux to return a score. is_similar_to((JFAMachine)self, …)Compares this JFABase with the ‘other’ one to be approximately the same. load((JFAMachine)self, (HDF5File)config)Loads the configuration parameters from a configuration file. save((JFAMachine)self, (HDF5File)config)Saves the configuration parameters to a configuration file. Attributes
dim_cThe number of Gaussian components dim_cdThe dimensionality of the supervector space dim_dThe dimensionality of the feature space dim_ruThe dimensionality of the within-class variations subspace (rank of U) dim_rvThe dimensionality of the between-class variations subspace (rank of V) jfa_baseThe JFABase attached to this machine xThe latent variable x (last one computed). yThe latent variable y of this machine zThe latent variable z of this machine -
__call__((MachineGMMStatsScalarBase)self, (GMMStats)input) → float :¶ Executes the machine on the GMMStats, and returns the (scalar) output. NO CHECK is performed.
-
dim_c¶ The number of Gaussian components
-
dim_cd¶ The dimensionality of the supervector space
-
dim_d¶ The dimensionality of the feature space
-
dim_ru¶ The dimensionality of the within-class variations subspace (rank of U)
-
dim_rv¶ The dimensionality of the between-class variations subspace (rank of V)
-
estimate_ux((JFAMachine)self, (GMMStats)stats, (object)ux) → None :¶ Estimates Ux (LPT assumption) given GMM statistics.
-
estimate_x((JFAMachine)self, (GMMStats)stats, (object)x) → None :¶ Estimates the session offset x (LPT assumption) given GMM statistics.
-
forward((MachineGMMStatsScalarBase)self, (GMMStats)input) → float :¶ Executes the machine on the GMMStats, and returns the (scalar) output.
-
forward_((MachineGMMStatsScalarBase)self, (GMMStats)input) → float :¶ Executes the machine on the GMMStats, and returns the (scalar) output. NO CHECK is performed.
-
forward_ux((JFAMachine)self, (GMMStats)stats, (object)ux) → float :¶ Processes the GMM statistics and Ux to return a score.
-
is_similar_to((JFAMachine)self, (JFAMachine)other[, (float)r_epsilon=1e-05[, (float)a_epsilon=1e-08]]) → bool :¶ Compares this JFABase with the ‘other’ one to be approximately the same.
-
jfa_base¶ The JFABase attached to this machine
-
load((JFAMachine)self, (HDF5File)config) → None :¶ Loads the configuration parameters from a configuration file.
-
save((JFAMachine)self, (HDF5File)config) → None :¶ Saves the configuration parameters to a configuration file.
-
x¶ The latent variable x (last one computed). This is a feature provided for convenience, but this attribute is not ‘part’ of the machine. The session latent variable x is indeed not class-specific, but depends on the sample considered. Furthermore, it is not saved into the machine or used when comparing machines.
-
y¶ The latent variable y of this machine
-
z¶ The latent variable z of this machine