NEW VERSION: the prosodic features of speech (simultaneous speech) compared to the features of native speech +++ spoken language proficiency level estimator
work on you need to do ML on your machine. Please contact me to get MLtraining.py and the relevant
*** Version-10 release: two new functions were added ***
The two new functions deploy different Machine Learning algorithms to estimate the speakers' spoken
language proficiency levels (only the prosody aspect not semantically).
Prosody is the study of the tune and rhythm of speech and how these features contribute to meaning.
Prosody is the study of those aspects of speech that typically apply to a level above that of the individual
phoneme and very often to sequences of words (in prosodic phrases). Features above the level of the phoneme
(or "segment") are referred to as suprasegmentals.
A phonetic study of prosody is a study of the suprasegmental features of speech. At the phonetic level,
prosody is characterised by:
1. vocal pitch (fundamental frequency)
2. acoustic intensity
3. rhythm (phoneme and syllable duration)
MyProsody is a Python library for measuring these acoustic features of speech (simultaneous speech, high entropy)
compared to ones of native speech. The acoustic features of native speech patterns have been observed and
established by employing Machine Learning algorithms. An acoustic model (algorithm) breaks recorded utterances
(48 kHz & 32 bit sampling rate and bit depth respectively) and detects syllable boundaries, fundamental frequency
contours, and formants. Its built-in functions recognize/measures:
f0_index ((f0 is for fundamental frequency)
(f2/f1)_mean (1st and 2nd formant frequencies)
speech mood (semantic analysis)
pronunciation posterior score
level (CEFR level)
prosody-aspects (comparison, native level)
The library was developed based upon the idea introduced by Klaus Zechner et al
*Automatic scoring of non-native spontaneous speech in tests of spoken English* Speech Communicaion vol
51-2009, Nivja DeJong and Ton Wempe , Paul Boersma and David Weenink , Carlo Gussenhoven ,
S.M Witt and S.J. Young  and Yannick Jadoul .
Peaks in intensity (dB) that are preceded and followed by dips in intensity are considered as potential
MyProsody is unique in its aim to provide a complete quantitative and analytical way to study acoustic
features of a speech. Moreover, those features could be analysed further by employing Python's
functionality to provide more fascinating insights into speech patterns.
This library is for Linguists, scientists, developers, speech and language therapy clinics and researchers.
Please note that MyProsody Analysis is currently in initial state though in active development. While the
amount of functionality that is currently present is not huge, more will be added over the next few months.
Myprosody can be installed like any other Python library, using (a recent version of) the Python package
manager pip, on Linux, macOS, and Windows:
pip install myprosody
or, to update your installed version to the latest release:
pip install -u myprosody
After installing Myprosody, download the folder called:
and save on your computer. The folder includes the audio files folder where you will save your audio files
Audio files must be in *.wav format, recorded at 48 kHz sample frame and 24-32 bits of resolution.
To check how the myprosody functions behave, please check
Myprosody was developed by MYOLUTIONS Lab in Japan. It is part of New Generation of Voice Recognition and Acoustic & Language modelling
Project in MYSOLUTIONS Lab. That is planned to enrich the functionality of Myprosody by adding more advanced
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
|Filename, size||File type||Python version||Upload date||Hashes|
|Filename, size myprosody-20-py3-none-any.whl (18.8 kB)||File type Wheel||Python version py3||Upload date||Hashes View|
|Filename, size myprosody-20.tar.gz (25.8 kB)||File type Source||Python version None||Upload date||Hashes View|