MayaFlux 1.0.0
Digital-First Multimedia Processing Framework
Loading...
Searching...
No Matches

◆ build_output()

template<ComputeData InputType = std::vector<Kakshya::DataVariant>, ComputeData OutputType = Kakshya::CompositeArray>
output_type MayaFlux::Yantra::PhonemeExtractor< InputType, OutputType >::build_output ( const PhonemeExtraction & record,
const std::vector< size_t > & rows,
std::span< const double > samples,
DataStructureInfo & info )
inlineprivate

Definition at line 379 of file PhonemeExtractor.hpp.

381 {
382 if constexpr (CompositeArrayData<OutputType>) {
383 info.composite_layout = phoneme_extraction_layout();
385 for (const size_t row : rows) {
386 const auto& event = record.events[row];
387 columns[0].push_back(static_cast<double>(event.phoneme));
388 columns[1].push_back(static_cast<double>(event.frame));
389 columns[2].push_back(static_cast<double>(event.sample));
390 columns[3].push_back(static_cast<double>(event.start));
391 columns[4].push_back(static_cast<double>(event.end));
392 columns[5].push_back(static_cast<double>(event.probability));
393 columns[6].push_back(HubertPhonemeModel::is_vowel(event.phoneme) ? 1.0 : 0.0);
394 columns[7].push_back(static_cast<double>(record.segments[row]));
395 }
397 for (size_t k = 0; k < rows.size(); ++k) {
398 output.data.set_text(k, "phoneme", HubertPhonemeModel::label(record.events[rows[k]].phoneme));
399 }
400 return output;
402 Kakshya::RegionGroup group("phonemes");
403 for (const auto& piece : pieces_of(record, rows)) {
404 const auto& event = record.events[piece.row];
405 auto region = Kakshya::Region::audio_span(piece.start, piece.end - 1, 0, 0,
407 region.set(phoneme_probability, static_cast<double>(event.probability));
408 region.set(phoneme_class, event.phoneme);
409 group.add_region(region);
410 }
412 output.data = std::move(group);
413 return output;
414 } else {
416 for (const auto& piece : pieces_of(record, rows)) {
417 ranges.emplace_back(piece.start, piece.end);
418 }
419 if (record.config.merge_adjacent) {
421 }
423 return this->convert_result(channel, info);
424 }
425 }
const Config & config() const
The stored config struct of type Config, or its defaults when none was set.
output_type convert_result(std::vector< std::vector< double > > &result_data, DataStructureInfo &metadata)
Convert processed double data back to OutputType using metadata and optional callback.
static std::vector< Piece > pieces_of(const PhonemeExtraction &record, const std::vector< size_t > &rows)
The phonemes of a whole mono 16 kHz recording, with the pauses between speech taken out.
std::vector< double > slice_intervals(std::span< const double > data, const std::vector< std::pair< size_t, size_t > > &intervals)
Copy data from a set of half-open intervals into a flat vector.
Definition Extract.cpp:63
std::vector< std::pair< size_t, size_t > > merge_intervals(const std::vector< std::pair< size_t, size_t > > &intervals)
Merge overlapping or adjacent half-open intervals.
Definition Extract.cpp:14
Kakshya::CompositeLayout phoneme_extraction_layout()
Field layout of the records a PhonemeExtractor gives: the phoneme record layout with the speech inter...
static Region audio_span(uint64_t start_frame, uint64_t end_frame, uint32_t start_channel, uint32_t end_channel, const std::string &label="")
Create a Region representing a span in audio (frames and channels).
Definition Region.hpp:196

Referenced by MayaFlux::Yantra::PhonemeExtractor< std::vector< Kakshya::DataVariant >, Kakshya::CompositeArray >::extract_implementation().

Here is the caller graph for this function: