Index

A

adjust_frame_length() (in module nnmnkwii.preprocessing) adjust_frame_lengths() (in module nnmnkwii.preprocessing) append() (nnmnkwii.io.hts.HTSLabelFile method)

apply_each2d_padded() (in module nnmnkwii.util) apply_each2d_trim() (in module nnmnkwii.util) asarray() (nnmnkwii.datasets.FileSourceDataset method) (nnmnkwii.datasets.PaddedFileSourceDataset method)

B

backward() (nnmnkwii.autograd.MLPG static method) (nnmnkwii.autograd.ModSpec static method) (nnmnkwii.autograd.UnitVarianceMLPG static method)

build_win_mats() (in module nnmnkwii.paramgen)

C

cache_size (nnmnkwii.datasets.MemoryCacheDataset attribute) (nnmnkwii.datasets.MemoryCacheFramewiseDataset attribute) cached_utterances (nnmnkwii.datasets.MemoryCacheDataset attribute) (nnmnkwii.datasets.MemoryCacheFramewiseDataset attribute) cholesky_inv() (in module nnmnkwii.util.linalg) cholesky_inv_banded() (in module nnmnkwii.util.linalg) collect_features() (nnmnkwii.datasets.FileDataSource method) collect_files() (nnmnkwii.datasets.cmu_arctic.WavFileDataSource method) (nnmnkwii.datasets.FileDataSource method) (nnmnkwii.datasets.jvs.TranscriptionDataSource method) (nnmnkwii.datasets.jvs.WavFileDataSource method) (nnmnkwii.datasets.ljspeech.TranscriptionDataSource method) (nnmnkwii.datasets.ljspeech.WavFileDataSource method) (nnmnkwii.datasets.vcc2016.WavFileDataSource method) (nnmnkwii.datasets.vctk.TranscriptionDataSource method) (nnmnkwii.datasets.vctk.WavFileDataSource method) (nnmnkwii.datasets.voice_statistics.TranscriptionDataSource method) (nnmnkwii.datasets.voice_statistics.WavFileDataSource method)

collected_files (nnmnkwii.datasets.FileSourceDataset attribute) contexts (nnmnkwii.io.hts.HTSLabelFile attribute) covarXX (nnmnkwii.baseline.gmm.MLPG attribute) covarXY (nnmnkwii.baseline.gmm.MLPG attribute) covarYX (nnmnkwii.baseline.gmm.MLPG attribute) covarYY (nnmnkwii.baseline.gmm.MLPG attribute)

D

D (nnmnkwii.baseline.gmm.MLPG attribute) Dataset (class in nnmnkwii.datasets) dataset (nnmnkwii.datasets.MemoryCacheDataset attribute) (nnmnkwii.datasets.MemoryCacheFramewiseDataset attribute)

delta_features() (in module nnmnkwii.preprocessing) dist (nnmnkwii.preprocessing.alignment.DTWAligner attribute) (nnmnkwii.preprocessing.alignment.IterativeDTWAligner attribute) DTWAligner (class in nnmnkwii.preprocessing.alignment) duration_features() (in module nnmnkwii.frontend.merlin)

E

end_times (nnmnkwii.io.hts.HTSLabelFile attribute) example_audio_file() (in module nnmnkwii.util) example_file_data_sources_for_acoustic_model() (in module nnmnkwii.util)

example_file_data_sources_for_duration_model() (in module nnmnkwii.util) example_label_file() (in module nnmnkwii.util) example_question_file() (in module nnmnkwii.util)

F

file_data_source (nnmnkwii.datasets.FileSourceDataset attribute) (nnmnkwii.datasets.PaddedFileSourceDataset attribute) FileDataSource (class in nnmnkwii.datasets)

FileSourceDataset (class in nnmnkwii.datasets) forward() (nnmnkwii.autograd.MLPG static method) (nnmnkwii.autograd.ModSpec static method) (nnmnkwii.autograd.UnitVarianceMLPG static method)

H

HTSLabelFile (class in nnmnkwii.io.hts)

I

interp1d() (in module nnmnkwii.preprocessing.f0) inv_minmax_scale() (in module nnmnkwii.preprocessing) inv_modspec() (in module nnmnkwii.preprocessing) inv_mulaw() (in module nnmnkwii.preprocessing)

inv_mulaw_quantize() (in module nnmnkwii.preprocessing) inv_preemphasis() (in module nnmnkwii.preprocessing) inv_scale() (in module nnmnkwii.preprocessing) IterativeDTWAligner (class in nnmnkwii.preprocessing.alignment)

L

labels (nnmnkwii.datasets.cmu_arctic.WavFileDataSource attribute) (nnmnkwii.datasets.jvs.TranscriptionDataSource attribute) (nnmnkwii.datasets.jvs.WavFileDataSource attribute) (nnmnkwii.datasets.vcc2016.WavFileDataSource attribute) (nnmnkwii.datasets.vctk.TranscriptionDataSource attribute) (nnmnkwii.datasets.vctk.WavFileDataSource attribute) (nnmnkwii.datasets.voice_statistics.WavFileDataSource attribute)

lf0_mean_squared_error() (in module nnmnkwii.metrics) linguistic_features() (in module nnmnkwii.frontend.merlin) load() (in module nnmnkwii.io.hts) (nnmnkwii.io.hts.HTSLabelFile method) load_question_set() (in module nnmnkwii.io.hts)

M

max_iter_gmm (nnmnkwii.preprocessing.alignment.IterativeDTWAligner attribute) mean_squared_error() (in module nnmnkwii.metrics) meanstd() (in module nnmnkwii.preprocessing) meanvar() (in module nnmnkwii.preprocessing) melcd() (in module nnmnkwii.metrics) MemoryCacheDataset (class in nnmnkwii.datasets) MemoryCacheFramewiseDataset (class in nnmnkwii.datasets) merlin_post_filter() (in module nnmnkwii.postfilters) metadata (nnmnkwii.datasets.ljspeech.TranscriptionDataSource attribute) (nnmnkwii.datasets.ljspeech.WavFileDataSource attribute) minmax() (in module nnmnkwii.preprocessing) minmax_scale() (in module nnmnkwii.preprocessing) minmax_scale_params() (in module nnmnkwii.preprocessing) MLPG (class in nnmnkwii.autograd) (class in nnmnkwii.baseline.gmm) mlpg() (in module nnmnkwii.autograd) (in module nnmnkwii.paramgen) mlpg_grad() (in module nnmnkwii.paramgen) ModSpec (class in nnmnkwii.autograd)

modspec() (in module nnmnkwii.autograd) (in module nnmnkwii.preprocessing) modspec_smoothing() (in module nnmnkwii.preprocessing) module nnmnkwii.autograd nnmnkwii.baseline.gmm nnmnkwii.datasets nnmnkwii.frontend.merlin nnmnkwii.io.hts nnmnkwii.metrics nnmnkwii.paramgen nnmnkwii.postfilters nnmnkwii.preprocessing nnmnkwii.preprocessing.alignment nnmnkwii.preprocessing.f0 nnmnkwii.util nnmnkwii.util.linalg mulaw() (in module nnmnkwii.preprocessing) mulaw_quantize() (in module nnmnkwii.preprocessing)

N

n_components_gmm (nnmnkwii.preprocessing.alignment.IterativeDTWAligner attribute) n_iter (nnmnkwii.preprocessing.alignment.IterativeDTWAligner attribute) nnmnkwii.autograd module nnmnkwii.baseline.gmm module nnmnkwii.datasets module nnmnkwii.frontend.merlin module nnmnkwii.io.hts module nnmnkwii.metrics module nnmnkwii.paramgen module

nnmnkwii.postfilters module nnmnkwii.preprocessing module nnmnkwii.preprocessing.alignment module nnmnkwii.preprocessing.f0 module nnmnkwii.util module nnmnkwii.util.linalg module num_mixtures (nnmnkwii.baseline.gmm.MLPG attribute) num_states() (nnmnkwii.io.hts.HTSLabelFile method)

P

padded_length (nnmnkwii.datasets.PaddedFileSourceDataset attribute) PaddedFileSourceDataset (class in nnmnkwii.datasets)

preemphasis() (in module nnmnkwii.preprocessing) px (nnmnkwii.baseline.gmm.MLPG attribute)

R

radius (nnmnkwii.preprocessing.alignment.DTWAligner attribute) (nnmnkwii.preprocessing.alignment.IterativeDTWAligner attribute)

remove_zeros_frames() (in module nnmnkwii.preprocessing) reshape_means() (in module nnmnkwii.paramgen)

S

scale() (in module nnmnkwii.preprocessing) set_durations() (nnmnkwii.io.hts.HTSLabelFile method) silence_frame_indices() (nnmnkwii.io.hts.HTSLabelFile method) silence_label_indices() (nnmnkwii.io.hts.HTSLabelFile method) silence_phone_indices() (nnmnkwii.io.hts.HTSLabelFile method)

speaker_info (nnmnkwii.datasets.jvs.TranscriptionDataSource attribute) (nnmnkwii.datasets.jvs.WavFileDataSource attribute) (nnmnkwii.datasets.vctk.TranscriptionDataSource attribute) (nnmnkwii.datasets.vctk.WavFileDataSource attribute) src_means (nnmnkwii.baseline.gmm.MLPG attribute) start_times (nnmnkwii.io.hts.HTSLabelFile attribute)

T

tgt_means (nnmnkwii.baseline.gmm.MLPG attribute) TranscriptionDataSource (class in nnmnkwii.datasets.jsut) (class in nnmnkwii.datasets.jvs) (class in nnmnkwii.datasets.ljspeech) (class in nnmnkwii.datasets.vctk) (class in nnmnkwii.datasets.voice_statistics)

transform() (nnmnkwii.baseline.gmm.MLPG method) trim_zeros_frames() (in module nnmnkwii.preprocessing)

U

unit_variance_mlpg() (in module nnmnkwii.autograd)

unit_variance_mlpg_matrix() (in module nnmnkwii.paramgen) UnitVarianceMLPG (class in nnmnkwii.autograd)

V

verbose (nnmnkwii.preprocessing.alignment.DTWAligner attribute) (nnmnkwii.preprocessing.alignment.IterativeDTWAligner attribute)

vuv_error() (in module nnmnkwii.metrics)

W

WavFileDataSource (class in nnmnkwii.datasets.cmu_arctic) (class in nnmnkwii.datasets.jsut) (class in nnmnkwii.datasets.jvs) (class in nnmnkwii.datasets.ljspeech) (class in nnmnkwii.datasets.vcc2016) (class in nnmnkwii.datasets.vctk) (class in nnmnkwii.datasets.voice_statistics)

weights (nnmnkwii.baseline.gmm.MLPG attribute) write_audacity_labels() (in module nnmnkwii.io.hts) write_textgrid() (in module nnmnkwii.io.hts)