| AccumAmDiagGmm | |
| AccumAmTiedDiagGmm | |
| AccumAmTiedFullGmm | |
| AccumDiagGmm | |
| AccumFullGmm | Class for computing the maximum-likelihood estimates of the parameters of a Gaussian mixture model |
| AccumTiedGmm | |
| AffineXformStats | |
| AmDiagGmm | |
| AmSgmm | Class for definition of the subspace Gmm acoustic model |
| AmSgmmFunctions | Class for misc functions that need access to SGMM private variables |
| AmTiedDiagGmm | |
| AmTiedFullGmm | |
| MinimumBayesRisk::Arc | |
| ComposeTrimmer< A, M >::ArcEqual | |
| ArcIterator< ContextFst< A > > | |
| ArcIterator< DeterministicOnDemandFst< A > > | |
| ArcIterator< TrivialFactorWeightFst< A, F > > | |
| ComposeTrimmer< A, M >::ArcSortCompareIlabelFirst | |
| ComposeTrimmer< A, M >::ArcSortCompareOlabelFirst | |
| basic_filebuf | |
| basic_pipebuf< CharType, Traits > | |
| BasicHolder< BasicType > | |
| BasicPairVectorHolder< BasicType > | BasicPairVectorHolder is a Holder for a vector of pairs of a basic type, e.g |
| BasicVectorHolder< BasicType > | A Holder for a vector of basic types, e.g |
| BasicVectorVectorHolder< BasicType > | BasicVectorVectorHolder is a Holder for a vector of vector of a basic type, e.g |
| BiglmFasterDecoder | This is as FasterDecoder, but does online composition between HCLG and the "difference language model", which is a deterministic FST that represents the difference between the language model you want and the language model you compiled HCLG with |
| BottomUpClusterer | |
| CacheArcIterator | |
| CacheImpl | |
| CacheOptions | |
| CacheStateIterator | |
| Clusterable | |
| ClusterKMeansOptions | |
| CompactLatticeHolder | |
| CompactLatticeWeightCommonDivisorTpl< BaseWeightType, IntType > | |
| CompactLatticeWeightTpl< WeightType, IntType > | |
| CompareFirstMemberOfPair< A, B > | Comparator object for pairs that compares only the first pair |
| CompartmentalizedBottomUpClusterer | |
| CompBotClustElem | |
| ComposeTrimmer< A, M >::ComposedArc | |
| ComposeTrimmer< A, M >::ComposedState | |
| ComposeTrimmer< A, M > | |
| ComposeTrimmerOptions | ComposeTrimmerOptions is an options class used by ComposeTrim |
| CompressVars | |
| LatticeWordAligner::ComputationState | |
| ComputationState | |
| ComputeNormalizersClass | |
| ConstantEventMap | |
| ConstIntegerSet< I > | |
| ContextDependency | |
| ContextDependencyInterface | Context-dep-itf.h provides a link between the tree-building code in ../tree/, and the FST code in ../fstext/ (particularly, ../fstext/context-dep.h) |
| ContextFst< Arc, LabelT > | |
| ContextFstImpl< Arc, LabelT > | |
| ContextMatcher< Arc, LabelT > | |
| CountStats | |
| DecisionTreeSplitter | |
| DecodableAmDiagGmm | |
| DecodableAmDiagGmmRegtreeFmllr | |
| DecodableAmDiagGmmRegtreeMllr | |
| DecodableAmDiagGmmScaled | |
| DecodableAmDiagGmmUnmapped | DecodableAmDiagGmmUnmapped is a decodable object that takes indices that correspond to pdf-id's plus one |
| DecodableAmSgmm | |
| DecodableAmSgmmFmllr | |
| DecodableAmSgmmScaled | |
| DecodableAmTiedDiagGmm | |
| DecodableAmTiedDiagGmmScaled | |
| DecodableAmTiedFullGmm | |
| DecodableAmTiedFullGmmScaled | |
| DecodableInterface | Decodable-itf.h provides a link between the (acoustic-modeling and feature-processing) code and the decoder |
| DecodableMapped | |
| DecodableMatrixScaled | |
| DecodableMatrixScaledMapped | |
| DecodableSum | |
| DecodeInfo | |
| Definition | Mixture Model with full covariances |
| DeltaFeatures | |
| DeltaFeaturesOptions | |
| DeterministicOnDemandFst< Arc > | |
| DeterministicOnDemandFstImpl< Arc > | |
| DeterminizeLatticeOptions | |
| DeterminizerStar< Arc > | |
| DfsOrderVisitor< Arc > | |
| DiagGmm | Gaussian Mixture Model with diagonal covariances |
| DiagGmmNormal | Definition for Gaussian Mixture Model with diagonal covariances in normal mode: where the parameters are stored as means and variances (instead of the exponential form that the DiagGmm class is stored as) |
| ParseOptions::DocInfo | Structure for options' documentation |
| EbwOptions | |
| EbwWeightOptions | |
| EigenvalueDecomposition< Real > | |
| HashList< I, T >::Elem | |
| LatticeDeterminizer< Weight, IntType >::Element | |
| DeterminizerStar< Arc >::Element | |
| TrivialFactorWeightFstImpl< A, F >::Element | |
| TrivialFactorWeightFstImpl< A, F >::ElementEqual | |
| TrivialFactorWeightFstImpl< A, F >::ElementKey | |
| LatticeStringRepository< IntType >::Entry | |
| LatticeStringRepository< IntType >::EntryEqual | |
| LatticeStringRepository< IntType >::EntryKey | |
| error_stats | |
| EventMap | A class that is capable of representing a generic mapping from EventType (which is a vector of (key, value) pairs) to EventAnswerType which is just an integer |
| EventMapVectorEqual | |
| EventMapVectorHash | |
| ExampleClass | |
| ExponentialTransform | |
| ExponentialTransformAccsA | |
| ExponentialTransformUpdateAOptions | |
| FasterDecoder | |
| FasterDecoderOptions | |
| Fbank | Class for computing FBANK features; see Computing MFCC features for more information |
| FbankOptions | FbankOptions contains basic options for computing FBANK features It only includes things that can be done in a "stateless" way, i.e |
| FeatureWindowFunction | |
| FileInputImpl | |
| FileOutputImpl | |
| FmllrDiagGmmAccs | This does not work with multiple feature transforms |
| FmllrDiagGradientDescent | |
| FmllrOptions | |
| FmllrSgmmAccs | Class for computing the accumulators needed for the maximum-likelihood estimate of FMLLR transforms for a subspace GMM acoustic model |
| Fmpe | |
| FmpeOptions | |
| FmpeUpdateOptions | |
| LatticeBiglmFasterDecoder::ForwardLink | |
| LatticeFasterDecoder::ForwardLink | |
| LatticeSimpleDecoder::ForwardLink | |
| FrameExtractionOptions | |
| Fst | |
| FullGmm | |
| FullGmmNormal | Definition for Gaussian Mixture Model with full covariances in normal mode: where the parameters are stored as means and variances (instead of the exponential form that the FullGmm class is stored as) |
| MinimumBayesRisk::GammaCompare | |
| GauPostHolder | |
| GaussClusterable | GaussClusterable wraps Gaussian statistics in a form accessible to generic clustering algorithms |
| GaussSelectionRecord | Used to select the top scoring Gaussians for each frame |
| GenericHolder< SomeType > | GenericHolder serves to document the requirements of the Holder interface; it's not intended to be used |
| HashList< I, T >::HashBucket | |
| HashList< I, T > | |
| HldaAccsDiagGmm | This class stores the compact form of the HLDA statistics, given a diagonal GMM |
| HmmCacheHash | |
| HmmTopology::HmmState | A structure defined inside HmmTopology to represent a HMM state |
| HmmTopology | A class for storing topology information for phones |
| HtkHeader | A structure containing the HTK header |
| HtkMatrixHolder | |
| HTransducerConfig | Configuration class for the GetHTransducer() function; see The HTransducerConfig configuration class for context |
| IdentityFunction< T > | |
| ImplToFst | |
| Input | |
| InputImplBase | |
| Int32IsZero | |
| KaldiCompileTimeAssert< B > | |
| KaldiCompileTimeAssert< true > | |
| KaldiDecoder< Decodable, Fst > | The main decoder class |
| KaldiDecoderOptions | |
| KaldiErrorMessage | |
| KaldiLogMessage | |
| KaldiObjectHolder< KaldiType > | |
| KaldiVlogMessage | |
| KaldiWarnMessage | |
| LangModelFst | Finite-state transducer language model |
| LatticeBiglmFasterDecoder | This is as LatticeFasterDecoder, but does online composition between HCLG and the "difference language model", which is a deterministic FST that represents the difference between the language model you want and the language model you compiled HCLG with |
| LatticeDeterminizer< Weight, IntType > | |
| LatticeFasterDecoder | A bit more optimized version of the lattice decoder |
| LatticeFasterDecoderConfig | |
| LatticeHolder | |
| LatticeReader | LatticeReader provides (static) functions for reading both Lattice and CompactLattice, in text form |
| LatticeSimpleDecoder | Simplest possible decoder, included largely for didactic purposes and as a means to debug more highly optimized decoders |
| LatticeSimpleDecoderConfig | |
| LatticeStringRepository< IntType > | |
| LatticeToStdMapper< Int > | Class LatticeToStdMapper maps a LatticeArc to a normal arc (StdArc) by adding the elements of the LatticeArc weight |
| LatticeWeightTpl< FloatType > | |
| LatticeWordAligner | |
| LdaEstimate | Class for computing linear discriminant analysis (LDA) transform |
| DecodableAmDiagGmmUnmapped::LikelihoodCacheRecord | Defines a cache record for a state |
| DecodableAmSgmm::LikelihoodCacheRecord | Defines a cache record for a state |
| DecodableAmTiedDiagGmm::LikelihoodCacheRecord | Defines a cache record for a pdf |
| DecodableAmTiedFullGmm::LikelihoodCacheRecord | Defines a cache record for a pdf |
| LinearVtln | |
| KaldiDecoder< Decodable, Fst >::LinkStore::Link | |
| KaldiDecoder< Decodable, Fst >::LinkStore | |
| LmFstConverter | Helper methods to convert toolkit internal representations into FST |
| LmTable | Basic Kaldi implementation for reading ARPA format files |
| MakeStochasticOptions | MakeStochasticOptions describes the options for the MakeStochasticFst and ReverseMakeStochasticFst functions |
| MapInputSymbolsMapper< Arc, I > | |
| MatcherBase | |
| Matrix< Real > | A class for storing matrices |
| MatrixBase< Real > | Base class which provides matrix operations not involving resizing or allocation |
| MatrixExponential< Real > | |
| MelBanks | |
| MelBanksOptions | |
| Mfcc | Class for computing MFCC features; see Computing MFCC features for more information |
| MfccOptions | MfccOptions contains basic options for computing MFCC features It only includes things that can be done in a "stateless" way, i.e |
| MinimumBayesRisk | The implementation of the Minimum Bayes Risk decoding method described in "Minimum Bayes Risk decoding and system combination based on a recursion for
edit distance", Haihua Xu, Daniel Povey, Lidia Mangu and Jie Zhu, Computer Speech and Language, 2011 This is a slightly more principled way to do Minimum Bayes Risk (MBR) decoding than the standard "Confusion Network" method |
| MleAmSgmmAccs | Class for the accumulators associated with the phonetic-subspace model parameters |
| MleAmSgmmOptions | Configuration variables needed in the SGMM estimation process |
| MleAmSgmmUpdater | Contains the functions needed to update the SGMM parameters |
| MleDiagGmmOptions | Configuration variables like variance floor, minimum occupancy, etc |
| MleFullGmmOptions | Configuration variables like variance floor, minimum occupancy, etc |
| MleSgmmSpeakerAccs | Class for the accumulators required to update the speaker vectors v_s |
| MleTiedGmmOptions | Configuration variables like minimum Gaussian weight |
| MlltAccs | A class for estimating Maximum Likelihood Linear Transform, also known as global Semi-tied Covariance (STC), for GMMs |
| MmieAccumDiagGmm | Class for computing the maximum mutual information estimate of the parameters of a Gaussian mixture model |
| MyThreadClass | |
| NaturalLess< CompactLatticeWeightTpl< LatticeWeightTpl< FloatType >, IntType > > | |
| NaturalLess< LatticeWeightTpl< FloatType > > | |
| NBestDecoder | |
| NBestDecoderOptions | |
| NCGOptions | @{ |
| TreeClusterer::Node | |
| NonlinearConjugateGradientsOptions< Real > | @{ |
| OffsetFileInputImpl | |
| OptimizableInterface< Real > | OptimizableInterface provides a virtual class for optimizable objects |
| OptimizeConfig | |
| OtherReal< T > | This class provides a way for switching between double and float types |
| OtherReal< double > | A specialized class for switching from double to float |
| OtherReal< float > | A specialized class for switching from float to double |
| Output | |
| OutputImplBase | |
| PackedMatrix< Real > | Packed matrix: base class for triangular and symmetric matrices |
| LatticeDeterminizer< Weight, IntType >::PairComparator | |
| DeterminizerStar< Arc >::PairComparator | |
| RandomAccessTableReaderSortedArchiveImpl< Holder >::PairCompare | |
| ParseOptions | The class ParseOptions is for parsing command-line options; see Parsing command-line options for more documentation |
| PipeInputImpl | |
| PipeOutputImpl | |
| Plp | Class for computing PLP features |
| PlpOptions | PlpOptions contains basic options for computing PLP features |
| RefineClusterer::point_info | |
| PosteriorHolder | |
| ProbCompare< A > | |
| QuadraticConjugateGradient | |
| QuadraticRprop | |
| Questions | This class defines, for each EventKeyType, a set of initial questions that it tries and also a number of iterations for which to refine the questions to increase likelihood |
| QuestionsForKey | QuestionsForKey is a class used to define the questions for a key, and also options that allow us to refine the question during tree-building (i.e |
| RandFstOptions | |
| RandomAccessTableReader< Holder > | Allows random access to a collection of objects in an archive or script file; see The Table concept |
| RandomAccessTableReaderArchiveImplBase< Holder > | |
| RandomAccessTableReaderDSortedArchiveImpl< Holder > | |
| RandomAccessTableReaderImplBase< Holder > | |
| RandomAccessTableReaderScriptImpl< Holder > | |
| RandomAccessTableReaderSortedArchiveImpl< Holder > | |
| RandomAccessTableReaderUnsortedArchiveImpl< Holder > | |
| RefineClusterer | |
| RefineClustersOptions | |
| RegressionTree | A regression tree is a clustering of Gaussian densities in an acoustic model, such that the group of Gaussians at each node of the tree are transformed by the same transform |
| RegtreeFmllrDiagGmm | An FMLLR (feature-space MLLR) transformation, also called CMLLR (constrained MLLR) is an affine transformation of the feature vectors |
| RegtreeFmllrDiagGmmAccs | Class for computing the accumulators needed for the maximum-likelihood estimate of FMLLR transforms for an acoustic model that uses diagonal Gaussian mixture models as emission densities |
| RegtreeFmllrOptions | Configuration variables for FMLLR transforms |
| RegtreeMllrDiagGmm | An MLLR mean transformation is an affine transformation of Gaussian means |
| RegtreeMllrDiagGmmAccs | Class for computing the maximum-likelihood estimates of the parameters of an acoustic model that uses diagonal Gaussian mixture models as emission densities |
| RegtreeMllrOptions | Configuration variables for FMLLR transforms |
| RemoveEpsLocalClass< Arc, ReweightPlus > | |
| RemoveSomeInputSymbolsMapper< Arc, I > | |
| ReweightPlusDefault< Weight > | |
| ReweightPlusLogArc | |
| RNN | |
| RnnLm | |
| RpropOptions< Real > | Options for the Rprop algorithm |
| RspecifierOptions | |
| ScalarClusterable | ScalarClusterable clusters scalars with x^2 loss |
| NBestDecoder::TokenStore::SeqToken | |
| SequentialTableReader< Holder > | A templated class for reading objects sequentially from an archive or script file; see The Table concept |
| SequentialTableReaderArchiveImpl< Holder > | |
| SequentialTableReaderImplBase< Holder > | |
| SequentialTableReaderScriptImpl< Holder > | |
| SgmmClusterable | This header defines an object that can be used to create decision trees using a form of SGMM statistics |
| SgmmCompressM | |
| SgmmFmllrConfig | Configuration variables needed in the estimation of FMLLR for SGMMs |
| SgmmFmllrGlobalParams | Global adaptation parameters |
| SgmmGauPost | Indexed by time |
| SgmmGauPostElement | This is the entry for a single time |
| SgmmGselectConfig | |
| SgmmPerFrameDerivedVars | Holds the per-frame precomputed quantities x(t), x_{i}(t), z_{i}(t), and n_{i}(t) (cf |
| SgmmPerSpkDerivedVars | |
| SimpleDecoder | Simplest possible decoder, included largely for didactic purposes and as a means to debug more highly optimized decoders |
| SphinxMatrixHolder< kFeatDim > | |
| SplitEventMap | |
| SplitRadixComplexFft< Real > | |
| SplitRadixRealFft< Real > | |
| SpMatrix< Real > | Packed symetric matrix class |
| StandardInputImpl | |
| StandardOutputImpl | |
| StateIterator< ContextFst< A > > | |
| StateIterator< DeterministicOnDemandFst< A > > | |
| StateIterator< TrivialFactorWeightFst< A, F > > | |
| DeterministicOnDemandFstImpl< Arc >::StatePairEqual | |
| DeterministicOnDemandFstImpl< Arc >::StatePairKey | |
| StdToLatticeMapper< Int > | Class StdToLatticeMapper maps a normal arc (StdArc) to a LatticeArc by putting the StdArc weight as the first element of the LatticeWeight |
| StringHasher | A hashing function object for strings |
| StringRepository< Label, StringId > | |
| SubMatrix< Real > | Sub-matrix representation |
| DeterminizerStar< Arc >::SubsetEqual | |
| LatticeDeterminizer< Weight, IntType >::SubsetEqual | |
| DeterminizerStar< Arc >::SubsetEqualStates | |
| LatticeDeterminizer< Weight, IntType >::SubsetEqualStates | |
| LatticeDeterminizer< Weight, IntType >::SubsetKey | |
| DeterminizerStar< Arc >::SubsetKey | |
| SubstateCounter | |
| SubVector< Real > | Represents a non-allocating general vector which can be defined as a sub-vector of higher-level vector [or as the row of a matrix] |
| TableComposeCache< F > | TableComposeCache lets us do multiple compositions while caching the same matcher |
| TableComposeOptions | |
| TableEventMap | |
| TableMatcher< F, BackoffMatcher > | |
| TableMatcherImpl< F, BackoffMatcher > | |
| TableMatcherOptions | TableMatcher is a matcher specialized for the case where the output side of the left FST always has either all-epsilons coming out of a state, or a majority of the symbol table |
| TableWriter< Holder > | A templated class for writing objects to an archive or script file; see The Table concept |
| TableWriterArchiveImpl< Holder > | |
| TableWriterBothImpl< Holder > | |
| TableWriterImplBase< Holder > | |
| TableWriterScriptImpl< Holder > | |
| LatticeDeterminizer< Weight, IntType >::TempArc | |
| DeterminizerStar< Arc >::TempArc | |
| TestFunctor< Arc > | |
| TidToTstateMapper | |
| TiedGmm | Definition for tied Gaussian mixture models |
| TiedGmmPerFrameVars | Holds the per-frame derived variables, namely the current feature vector, posteriors of the soft vector quantizer (svq) and an indicator if the latter are current w.r.t |
| Timer | |
| FasterDecoder::Token | |
| LatticeFasterDecoder::Token | |
| BiglmFasterDecoder::Token | |
| LatticeSimpleDecoder::Token | |
| KaldiDecoder< Decodable, Fst >::LinkStore::Token | |
| NBestDecoder::TokenStore::Token | |
| LatticeBiglmFasterDecoder::Token | |
| KaldiDecoder< Decodable, Fst >::WordLinkStore::Token | |
| SimpleDecoder::Token | |
| TokenHolder | |
| LatticeBiglmFasterDecoder::TokenList | |
| LatticeSimpleDecoder::TokenList | |
| LatticeFasterDecoder::TokenList | |
| KaldiDecoder< Decodable, Fst >::TokenSet< StateId > | |
| NBestDecoder::TokenStore | |
| KaldiDecoder< Decodable, Fst >::TokenStore | |
| TokenVectorHolder | |
| TpMatrix< Real > | Packed symetric matrix class |
| TrainingGraphCompiler | |
| TrainingGraphCompilerOptions | |
| TransitionModel | |
| TransitionUpdateConfig | |
| TreeClusterer | |
| TreeClusterOptions | |
| TreeRenderer | |
| TransitionModel::Triple | |
| TrivialFactorWeightFst< A, F > | FactorWeightFst takes as template parameter a FactorIterator as defined above |
| TrivialFactorWeightFstImpl< A, F > | |
| TrivialFactorWeightOptions< Arc > | |
| LatticeWordAligner::Tuple | |
| LatticeWordAligner::TupleEqual | |
| LatticeWordAligner::TupleHash | |
| UbmClusteringOptions | |
| UpdatePhoneVectorsCheckedFromClusterableClass | |
| UpdatePhoneVectorsClass | |
| UpdateWParallelClass | |
| Vector< Real > | A class representing a vector |
| vector | |
| VectorBase< Real > | Provides a vector abstraction class |
| StringRepository< Label, StringId >::VectorEqual | |
| VectorFst | |
| VectorFstHolder | |
| VectorHasher< Int > | A hashing function-object for vectors |
| StringRepository< Label, StringId >::VectorKey | |
| WaveData | This class's purpose is to read in Wave files |
| WaveHolder | |
| WordAlignedLatticeTester | |
| WordBoundaryInfo | |
| WordBoundaryInfoNewOpts | |
| WordBoundaryInfoOpts | ComposeSpecial is a special kind of composition algorithm |
| WordBoundaryInfoOpts | |
| KaldiDecoder< Decodable, Fst >::WordLinkStore::WordLink | |
| KaldiDecoder< Decodable, Fst >::WordLinkStore | |
| WspecifierOptions | |
1.7.3 
