openspeechlib

This is a package that includes several utilities to extract information from a speech signal, download open speech resources and others related speech activities.

Currently openspeechlib is in active development, if you have suggestion, requests of improvements please leave a issue using the Github Issue system for this repository

Some useful links

• Feature Extraction

  • MFCC
  • LibRosa
  • Speech Features
  • Numpy ML
  • Speech Signal Processing and Classification
  • Sonopy
  • SpeechPy
  • PLP
  • LFCC
  • WPF
  • SBC
  • MWP-ACE
  • PNCC
  • Power Normalized Cepstral Coefficients for Robust Speech Recognition
  • EVALUATION OF PNCC AND EXTENDED SPECTRAL SUBTRACTION METHODS FOR ROBUST SPEECH RECOGNITION
  • PNCC

• Model Training

  • DTW
  • DTW Speech Recognition
  • HMM
  • Speech Processing for machine learning
  • ANN
  • Deep Speech

• Aligners

  • Alignment Duration
  • Montreal Forced Aligner
  • Prosodylab Aligner
  • Praat
  • SPPAS

• Recognizers

  • HMM
  • Digit Recognizer
  • Speaker Recognition

• Generators

  • espeak-ng

• Applications

  • Speaker Identification
  • Emotion Recognition
  • Gender Recognition

Logging

If you want verbose information of the process please use in your script

import logging
logging.basicConfig(level=logging.DEBUG)