MayaFlux 1.0.0
Digital-First Multimedia Processing Framework
Loading...
Searching...
No Matches
PhonemeAnalyzer.hpp File Reference

Which phoneme is spoken near each 20 ms frame of an utterance, from a learned network run on the GPU. More...

Include dependency graph for PhonemeAnalyzer.hpp:
This graph shows which files directly or indirectly include this file:

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.

Detailed Description

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.