|
MayaFlux 1.0.0
Digital-First Multimedia Processing Framework
|
Which phoneme is spoken near each 20 ms frame of an utterance, from a learned network run on the GPU. More...
#include "MayaFlux/Transitive/Reflect/Describe.hpp"#include "MayaFlux/Transitive/Reflect/EnumReflect.hpp"#include "MayaFlux/Yantra/OperationSpec/OperationHelper.hpp"#include "Analyzer.hpp"#include <Eigen/Dense>#include "MayaFlux/Kakshya/Source/TensorContainer.hpp"#include "MayaFlux/Yantra/Executors/Audio/HubertPhonemeModel.hpp"#include "MayaFlux/Journal/Archivist.hpp"#include "PhonemeAnalyzer.describe.hpp"Go to the source code of this file.
Classes | |
| struct | MayaFlux::Yantra::PhonemeAnalysis |
| Analysis result of a PhonemeAnalyzer. More... | |
| class | MayaFlux::Yantra::PhonemeAnalyzer< InputType, OutputType > |
| Which phoneme is spoken near each frame of a mono 16 kHz utterance, from a learned network. More... | |
| struct | MayaFlux::Yantra::PhonemeAnalyzerConfig |
| Settings of a PhonemeAnalyzer. More... | |
| struct | MayaFlux::Yantra::PhonemeEvent |
| One phoneme the network recognised. More... | |
Namespaces | |
| namespace | MayaFlux |
| Main namespace for the Maya Flux audio engine. | |
| namespace | MayaFlux::Yantra |
Typedefs | |
| using | MayaFlux::Yantra::CompositePhonemeAnalyzer = PhonemeAnalyzer<std::vector<Kakshya::DataVariant>, Kakshya::CompositeArray> |
| Record phoneme analyzer: DataVariant -> one Composite record per recognised phoneme. | |
| using | MayaFlux::Yantra::ContainerPhonemeAnalyzer = PhonemeAnalyzer<std::shared_ptr<Kakshya::SignalSourceContainer>, Eigen::MatrixXd> |
| Container phoneme analyzer: SignalContainer -> MatrixXd. | |
| using | MayaFlux::Yantra::StandardPhonemeAnalyzer = PhonemeAnalyzer<std::vector<Kakshya::DataVariant>, Eigen::MatrixXd> |
| Standard phoneme analyzer: DataVariant -> MatrixXd. | |
Enumerations | |
| enum class | MayaFlux::Yantra::PhonemeMethod : uint8_t { MayaFlux::Yantra::POSTERIORS , MayaFlux::Yantra::BROAD_CLASSES , MayaFlux::Yantra::HELD_CLASSES } |
| The per-frame values a PhonemeAnalyzer reports as its output data. More... | |
Functions | |
| Kakshya::CompositeLayout | MayaFlux::Yantra::phoneme_record_layout () |
| Field layout of the records a PhonemeAnalyzer with Composite output gives, one record per recognised phoneme. | |
| Kakshya::RegionGroup | MayaFlux::Yantra::phoneme_regions (const PhonemeAnalysis &analysis, uint32_t first_channel, uint32_t last_channel, std::string name="phonemes") |
| One region per recognised phoneme, labelled with its ARPABET symbol. | |
Variables | |
| const Facet< uint32_t > | MayaFlux::Yantra::phoneme_class {} |
| Region attribute: the class of the region's phoneme. | |
| const Facet< double > | MayaFlux::Yantra::phoneme_probability {} |
| Region attribute: the probability the network gave the region's phoneme. | |
Which phoneme is spoken near each 20 ms frame of an utterance, from a learned network run on the GPU.
Definition in file PhonemeAnalyzer.hpp.