1.0
Contents
Installation
Installation on Linux
Installation from conda
Installation from sources
Installation on MacOS
Installation on Windows
Installation on Docker
Build the documentation
Introduction to speech features
Implemented models
Features comparison
Command line interface
Simple exemple
Definition of
<input-config>
Definition of
<input-utterances>
Definition of
<output-file>
Python API reference
Audio data
Features extraction
Spectrogram
Filterbank
MFCC
PLP
Bottleneck
One hot encoding
Pitch estimation using Kaldi
Pitch estimation using CREPE
Energy
VTLN
UBM
Features post-processing
CMVN
Delta features
Voice Activity Detection
Features extraction pipeline
Features manipulation
Features
Features collection
Supported file formats
Utterances
Utilities
Framing and windowing
Frames extraction
Windows functions
Time alignments
Abstract base classes
Base processor
Base processor
Base post-processor
Miscellaneous
shennong
»
Python API reference
»
Features post-processing
Features post-processing
ΒΆ
The available speech features post-processors are:
CMVN
Delta features
Voice Activity Detection