| config_var_type | Configuration variable description structure |
| fea_type | Feature matrix along with its meta data |
| rgba_type | Color structure |
| SAcousticSMSubsystemI | Modelling of acoustic features of a signal |
| SActiveWaveformPartSelectorI | Selects active waveform part of given start time and length |
| SAlignerI | Phoneme aligner |
| SAsyncFuncCallbackI | An interface that allows to run processing in a second thread by SAsyncFuncI |
| SAsyncFuncI | Runs a function in a second thread |
| SAudioFileI | This is a base class for all audio file format readers and writers |
| SAudioWaveformSourceI | Microphone input |
| SAudioWaveformTargetI | Speaker output |
| SBlockSetI | A block set to create and link blocks according to a config file |
| SCalibrationI | Maps labels according a set of rules |
| SChannelCallbackI | An interface that allows to receive actual channel index |
| SChannelSetterI | Sets the actual channel to the incoming STranscriptionI container and sends it to the target |
| SChannelSplitterI | Splits waveform channels and resends them separately |
| SCharSetI | Conversation between charsets and charset dependent string functions |
| SCIPhnLoopKWSNetGenI | This is simple KWS network generator with context independent models and phoneme loop in background |
| SCmllrEstimatorI | Very easy and fast decoder with hard wired phoneme loop |
| SConfigureCallbackI | An interface that enables to check and/or modify config line right after it is read from config file before it is processed by SConfigureI |
| SConfigureI | A class for configuration file reading and accessing configuration variables |
| SDataEncoderI | Data encoder |
| SDataStreamNodeI | Allows to split processing into two parts by saving features, segmentation and channel |
| SDecoderI | A base class for all decoders |
| SDiarizerI | Speaker diarization |
| segm_pos_type | One record in segmentation |
| SEigenChannelsFAI | Factor analysis based on eigen channels |
| SERestI | Reestimation of Hidden Markov Models |
| SErrorCallbackI | An interface that allows to receive error, warning and log messages |
| SErrorHandlerI | Creates and maintains object specific error handlers and keeps a list of recent text messages |
| SESpeakersEChannelsFAI | Factor analysis that models speaker variability, remaining speaker variability and channel variability |
| SF0EstimateToSegmConvertorI | Converts the fundamental frequency estimate to segmentation |
| SF0EstimatorI | Fundamental frequency estimator |
| SF0SmoothingI | Smoothing of transitions between F0 estimates and other states |
| SFactorAnalysisI | Basic class for all different factor analysis applyable to SGMMI |
| SFactorsI | Basic class for different factors used in factor analysis |
| SFeaCatI | Arbitrary feature transform described by a STK macro language |
| SFeaPasteI | Pastes two streams of feature matrices to one. Similar to GNU paste |
| SFeatureChunkerI | Split feature matrix into chunks |
| SFeatureDumperI | Allows to dump incoming feature matrix to a file and send it further |
| SFeatureExtractionCallbackI | An interface that allows to receive features |
| SFeatureExtractionI | A base class for all feature extractors |
| SFeatureJoinerI | Joins more feature segments together |
| SFeatureMatrixToIVectorsConvertorI | Convert matrix of floats into IVectors |
| SFeatureMemoryI | This memory can save feature matrix for later use |
| SFeatureNodeI | Forwards features from input to output |
| SFeatureSegmenterI | Receives features and segmentation and resends features by segments |
| SFeatureSelectorI | Receives features and segmentation and resends features by segments |
| SFeatureSplitterI | Sends features to multiple feature callback targets |
| SFeatureTransformI | A base class for all feature transforms |
| SFileListCallbackI | An interface that allow to receive information from SFileListI |
| SFileListI | Processing of file lists |
| SFileLockI | Provide file locking facility. Optionally it is possible to set automatic file deletion at its unlock |
| SFileSnifferCallbackI | An interface that allows to receive information from from SFileSnifferI |
| SFileSnifferI | Repeatedly scans directories and sends the new files to a callback, or just scan directories and return files to a user |
| SFileWaveformPlayerI | Simple audio file playback |
| SFileWaveformSourceI | Reads waveform files |
| SFloatMatrixI | Matrix of floats (usually features) |
| SFMinSearch1DI | Search for a minimum of 1D function |
| SFrequencyFilterI | Infinite impulse response (IIR) frequency filter |
| SFSTTargetI | Stores incoming STransFSTI transcription to a file |
| SFSTToConfusionNetworkConvertorI | Convertor from finite state transducer to confusion network |
| SFunction1DI | A base class for all functions that can be searched for a minimum by the SFMinSearch1DI searcher |
| SG2PI | Grapheme to phoneme convertor |
| SGenderID2I | Gender Identification System |
| SGenderIDI | Gender Identification System |
| SGMMBasedEstimatorI | GMM based estimator (for fast VTLN, GID, etc.) |
| SGMMDecoderI | A classifier based on Gaussian Mixture Models |
| SGMMI | Gaussian Mixture Model |
| SGMMListI | List of Gaussian mixture models |
| SGMMModelListI | Adaptor of SGMMListI to SModelListI |
| SGMMPreselectionTableI | Gaussian pre-selection table for the GMM evaluation speed-up |
| SGMMStatisticCollectorI | Collection of GMM statistics for several speaker identification systems |
| SGrammarCompilerGroupI | Grammar compiler group |
| SGrammarCompilerI | Grammar compiler |
| SGrammarListI | Grammar list |
| SIndexesToSegmConvertorI | Cluster of indexes to segmentation convertor |
| SIntMatrixI | Matrix of integers (usually features) |
| SIsolatedWordRecognizerI | Isolated word recognizer |
| SIVectorExtractorI | Extraction of iVectors from GMM statistics fro speaker recognition |
| SIVectorModelListI | IVector model list |
| SIVectorsToFeatureMatrixConvertorI | Convert iVectors into matrix of floats (features) |
| SIVectorToVoicePrintConvertorI | Encapsulate iVector to voice-print |
| SKaldiDecoderI | LVCSR decoder based on the Kaldi library |
| SKeywordDetectionFilterI | Keyword detection filter |
| SKeywordDurationModelI | Keyword duration model |
| SKeywordI | Container for one keyword in keyword list |
| SKeywordListI | Keyword list |
| SKeywordScoreNormI | Keyword score normalization |
| SKeywordSpottingI | Keyword spotting system |
| SKeywordThresholdI | Keyword threshold |
| SKWSDecoderI | Keyword spotting decoder based on the STK library |
| SKWSNetworkGeneratorI | This is basic class for KWS nework generators for SKWSDecoderI |
| SLabelAdjusterI | Adjusts label boundaries according adjustment rules |
| SLabelClustererI | Merges labels to the clusters of a specified length |
| SLabelMapperI | Maps labels according a set of rules |
| SLexiconI | A Lexicon with words and their phonetic transcriptions |
| SLicenseManagerI | License manager |
| SLID2I | Language Identification System |
| SLIDI | Language Identification System |
| SLinearTransformI | Precomputed linear transform (e.g. DCT) |
| SMeanEstimationI | Estimation of means |
| SMelBanksI | Calculation of Mel-bank energies |
| SMFCCI | Calculation of Mel Frequency Cepstral Coefficients |
| SModelListI | List of models |
| SMulticoreI | Base class for all multicore functions |
| SMulticoreVoicePrintExtractorI | SMulticoreVoicePrintExtractorI |
| SNetworkI | Network used with SGrammarCompilerI |
| SNGramPhonotacticModelListI | N-gram phonotactic model list for SSignalModelling2I |
| SNGramPhonotacticModelsI | Modeling of phonotactic dependencies using n-gram language models |
| SNNetPosteriorEstimatorI | Posterior probability of labels (phonemes) estimator based on artificial neural networks |
| SNormalizationI | Mean and variance normalization of features |
| SObjectMemoryI | Allows memory sharing |
| SOfflineNormalizationI | Mean and variance normalization of features |
| SOfflineSpeechRecCallbackI | An interface that allows to receive information from SOfflineSpeechRecognizerI |
| SOfflineSpeechRecognizer3I | Offline speech recognizer with VAD, segment based mean and variance normalization and fast VTLN estimation |
| SOfflineSpeechRecognizerI | Offline speech recognizer with VAD, segment based mean and variance normalization and fast VTLN estimation |
| SOnlineFeatureSegmenterI | Receives features and segmentation and resends features by segments |
| SOnlineSpeechRecognizerI | Online speech recognizer with microphone calibration |
| SOnlineWaveformSegmenterI | Receives waveform and segmentation and resends waveform by segments -online |
| SParamCmllrI | Parameters container - CMLLR matrix |
| SParametersCallbackI | An interface that enables to receive parameters (e.g. normalization parameters) |
| SParametersI | A base class for all possible parameters containers |
| SParametersNodeI | Forwards parameters from input to output |
| SParametersSplitterI | Allows to call multiple parameters callback functions as one callback call |
| SParamGMMEstimI | Parameters container - actual factor and scores counted by SGMMBasedEstimatorI |
| SParamIndexClusterI | Parameters container - cluster of indexes |
| SParamIVectorI | Parameters container - iVector speaker parameters |
| SParamNormI | Parameters container - normalization parameters (means, variances, global variances) |
| SPhnDecoderI | Very easy and fast decoder with hard wired phoneme loop |
| SPhnTransI | This class merges transcription from a lexicon and G2P |
| SPhonemeBasedCalibrationI | Phoneme based calibration |
| SPhoneticLabelExpansionI | Phonetic label expansion |
| SPhonotacticModelsI | A base class for a phonotactic modelling approach used by SPhonotacticSMSubsystemI |
| SPhonotacticSMSubsystemI | Modelling of phonotactic dependencies in speech signal |
| SPieceWiseFunc2DI | Evaluate 2D function aproximated by a table |
| SPieceWiseScoreScaleI | Training/test segment length dependent calibration |
| SPLPI | Calculation of Perceptual Linear Prediction features |
| SPronunciationI | One pronunciation variant in pronunciation list |
| SPronunciationListI | Pronunciation list |
| SRandomGeneratorI | Random value generator |
| SRawFileI | Raw file format reader and writer |
| SRiffFileI | Reads RIFF file format |
| SScoreCallbackI | An interface that enables to receive scores |
| SScoreDumperI | Allows to dump incoming scores to a file and send it further |
| SScoreMemoryI | Remembers one score container for later use |
| SScoreMergerI | Score merger |
| SScoreNodeI | Score node |
| SScoresI | Scores |
| SScoreTransformI | Score transformations |
| SSegmentationI | Produces speech/nonspeech segmentation |
| SSegmentMapperI | Segment mapper maps segment boundaries to their original times before using VAD, waveform filter etc |
| SSignalModelling2I | Modelling and classification (or detection) of arbitrary signals |
| SSignalModellingI | Modelling and classification (or detection) of arbitrary signals |
| SSignalModellingSubsystemI | Base class for all signal modelling subsystems |
| SSpeakerChannelFactorsI | Speaker and channel factors for SESpeakersEChannelsFAI |
| SSpeakerID2I | Speaker Identification System |
| SSpeakerIDI | Speaker Identification System |
| SSpeechFilePreselectorI | Speech file preselector |
| SSpeechRecI | Speech recognizer |
| SSpeechRecStateCallbackI | An interface that allows to receive a state information from SSpeechRecI |
| SStatisticsCallbackI | An interface that enables to receive statistics (e.g. CMLLR statistics) |
| SStatisticsI | A base class for all possible statistics containers |
| SStatisticsNodeI | Forwards statistics from input to output |
| SStatsCmllrI | Statistics container - CMLLR |
| SStatsGMMI | Statistics container - GMM statistics - zero, first and second order statistics |
| SSTGI | Short time Gaussianization |
| SSTKDecoderI | LVCSR decoder with a static recognition network based on the STK library |
| SSTKLatticeToFSTConvertorI | Convertor from STK lattice to OpenFST finite state transducer |
| STextMessageI | A container that is used to store (error, warning and log) message parameters |
| STransCallbackI | An interface that allows to receive segmentation from a decoder |
| STranscriptionCharsetConvertorI | Converts charset of words in STransOneWordI container |
| STranscriptionDistributerI | Distributes transcription to the specific target depending on container type |
| STranscriptionDumperI | Allows to dump incoming transcription to a file and send it further |
| STranscriptionI | A base class for all possible transcriptions containers sent by decoders or received by the STranscriptionMemoryI::GetTranscription() |
| STranscriptionJointerI | Joins transcription's time - removes spaces between two consequent label |
| STranscriptionMemoryI | This memory can save transcription that came at input for later use |
| STranscriptionNodeI | Forwards transcription from input to output |
| STranscriptionSegmenterI | Receives transcriptions and segmentation and resends segmented transcription with IsLast after each segment |
| STranscriptionSplitterI | Allows to call multiple transcription callback functions as one callback call |
| STranscriptionTargetI | Stores incoming STransOneWordI transcription to a file |
| STransFSTExtensionI | Extension to FST with speech transcription |
| STransFSTI | Transcription container - OpenFST finite state transducer |
| STransLatticeI | Transcription container - lattice - a graph of many hypothesized speech transcriptions |
| STransOneBestI | Transcription container - the best path |
| STransOneWordI | Transcription container - one word |
| STransPosteriorsI | Transcription container - posterior probabilities of occurrence of labels in transcribed speech calculated from a lattice |
| STransSegmentationArrayI | Transcription container - array of segmentation boundaries |
| STwoCovarianceModelI | Two covariance model |
| STwoSetComparisonI | Comparison of two sets of vectors |
| STwoSetPieceWiseScoreScaleI | Length dependent calibration working on a score matrix for two sets (training and test) |
| SUnknownI | Base class for all BSAPI interfaces |
| SUserCalibrationI | User calibration |
| SVectorQuantizerI | Vector quantization |
| SVoicePrintComparatorI | Voice-print comparator |
| SVoicePrintExtractorI | Voice-print extractor |
| SVoicePrintI | Voice-print - an unique biometric identificator that describes speaker |
| SVoicePrintModelListI | Voice-print model list for SSignalModelling2I |
| SVoicePrintSetI | Voice-print set |
| SVoicePrintUserCalibrationI | Voice-print user calibration |
| SVtlnOfflineI | Search for the warping factor for Vocal Tract Length Normalization |
| SWaveFileI | MS WAVE format reader and writer |
| SWaveformDataI | Waveform data used with some of the SWaveformEditorPanelI |
| SWaveformEditorCallbackI | An interface that allows to draw on a panel |
| SWaveformEditorHighlightingI | One highlighting |
| SWaveformEditorHighlightingListI | List of highlighting |
| SWaveformEditorI | Provides panels synchronization |
| SWaveformEditorPanelI | Base class for all panels |
| SWaveformFilterI | Cut off technical noises and long silence parts form waveform |
| SWaveformFormatConvertorI | Converts different waveform formats to floats |
| SWaveformI | A container for storing a waveform |
| SWaveformJoinerI | Joins more waveform segments together |
| SWaveformMemoryI | Makes a copy of waveform block for later use |
| SWaveformNodeI | Forwards waveform from input to output |
| SWaveformResamplerI | Converts a waveform from a given sampling rate to a different sampling rate |
| SWaveformResegmenterI | Cut off silense parts from waveform and produce new segmentation labels |
| SWaveformSegmenterI | Receives waveform and segmentation and resends waveform by segments |
| SWaveformSelectorI | Receives waveform and segmentation and resends waveform by segments |
| SWaveformSourceCallbackI | An interface that allows to receive waveform |
| SWaveformSourceI | A base class for all waveform sources (SAudioWaveformSourceI, SFileWaveformSourceI) |
| SWaveformSplitterI | Allows to call multiple OnWaveform callback functions as one callback call |
| SWaveformTargetI | A base class for all waveform targets (now only SAudioWaveformTargetI) |
| SWEPLabelPanelI | Show transription |
| SWEPPowerPanelI | Show waveform |
| SWEPTimePanelI | Show time axis |
| SWEPWaveformPanelI | Show waveform |
| SXMLDocumentI | XML document |
| SXMLNodeI | XML node |
| SXMLPropertiesI | XML node properties |
| te_type | Phonetic transcription from SLexiconI, SG2PI or SPhnTransI |
