CRAFT: A multifunction online platform for speech prosody visualisation

03/18/2019
by   Dafydd Gibbon, et al.
0

There are many research tools which are also used for teaching the acoustic phonetics of speech rhythm and speech melody. But they were not purpose-designed for teaching-learning situations, and some have a steep learning curve. CRAFT (Creation and Recovery of Amplitude and Frequency Tracks) is custom-designed as a novel flexible online tool for visualisation and critical comparison of functions and transforms, with implementations of the Reaper, RAPT, PyRapt, YAAPT, YIN and PySWIPE F0 estimators, three Praat configurations, and two purpose-built estimators, PyAMDF, S0FT. Visualisations of amplitude and frequency envelope spectra, spectral edge detection of rhythm zones, and a parametrised spectrogram are included. A selection of audio clips from tone and intonation languages is provided for demonstration purposes. The main advantages of online tools are consistency (users have the same version and the same data selection), interoperability over different platforms, and ease of maintenance. The code is available on GitHub.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/16/2020

Knowledge-and-Data-Driven Amplitude Spectrum Prediction for Hierarchical Neural Vocoders

In our previous work, we have proposed a neural vocoder called HiNet whi...
research
09/03/2019

Quantifying and Correlating Rhythm Formants in Speech

The objective of the present study is exploratory: to introduce and appl...
research
05/31/2020

Maximum Voiced Frequency Estimation: Exploiting Amplitude and Phase Spectra

Maximum Voiced Frequency (MVF) is used in various speech models as the s...
research
09/05/2022

Gather – a better way to codehack online

A virtual hands-on computer laboratory has been designed within the Gath...
research
06/23/2019

A Neural Vocoder with Hierarchical Generation of Amplitude and Phase Spectra for Statistical Parametric Speech Synthesis

This paper presents a neural vocoder named HiNet which reconstructs spee...
research
06/05/2018

LSTM Benchmarks for Deep Learning Frameworks

This study provides benchmarks for different implementations of LSTM uni...
research
04/23/2018

The Future of Prosody: It's about Time

Prosody is usually defined in terms of the three distinct but interactin...

Please sign up or login with your details

Forgot password? Click here to reset