|
|||||||||
| PREV PACKAGE NEXT PACKAGE | FRAMES NO FRAMES | ||||||||
See:
Description
| Interface Summary | |
|---|---|
| ConfidenceResult | Shows the confidence information about a Result. |
| ConfidenceScorer | Computes confidences for a Result. |
| Path | Represents a path of words through the recognition result lattice. |
| WordResult | Represents a word in a recognition result. |
| Class Summary | |
|---|---|
| AbstractSausageMaker | Parent to all sausage makers. |
| ConfusionSet | A confusion set is a set of words with their associated posteriors. |
| Edge | Edges are part of Lattices. |
| FrameStatistics | Contains statistics about a frame. |
| GDLLatticeFactory | Creates a Lattice from a GDL (AISee) Lattice file. |
| Lattice | Provides recognition lattice results. |
| LatticeOptimizer | Class used to collapse all equivalent paths in a Lattice. |
| LatticeRescorer | Class rescore the lattice with the new Language model. |
| MAPConfidenceScorer | Computes confidences for the highest scoring path in a Result. |
| Node | A node is part of Lattices, representing the theory that a word was spoken over a given period of time. |
| PivotSausageMaker | This is an implementation of an alternative sausage making algorithm as described in the following paper. |
| Result | Provides recognition results. |
| Sausage | A Sausage is a sequence of confusion sets, one for each position in an utterance. |
| SausageMaker | The SausageMaker takes word lattices as input and turns them into sausages (Confusion Networks) according to Mangu, Brill and Stolcke, "Finding Consensus in Speech Recognition: word error minimization and other applications of confusion networks", Computer Speech and Language, 2000. |
| SimpleWordResult | Represents a single word result with associated scoring and timing information. |
| TokenGraphDumper | Dumps out the GDL graph of all the result token chains in a Result, as well as all the alternate hypotheses along those chains. |
| WordResultPath | An implementation of a result Path that computes scores and confidences on the fly. |
Provides a set of classes that represent the result of a recognition. Results can maintained in a lattice, which is a directed graph of all the possible words recognized.
|
|||||||||
| PREV PACKAGE NEXT PACKAGE | FRAMES NO FRAMES | ||||||||