Coder Social home page Coder Social logo

speechvis's Introduction

speechvis

This project provides a set of tools for segmenting, analyzing, and visualizing recorded speech. In particular, the goal is to treat segmented speech from the Warlaumont IVFCR corpus as high-dimensional time-series, and provide a library of analyses to reveal the structure within these high-dimensional data.

Features

  • Parse LENA ITS files to extract segment boundaries and labels for entire recordings.
  • Plot speaker counts, durations, intervals, and volubility for parsed recordings.
  • Segment WAV file recordings to save segments as individual, categorized files.
  • Generate and plot acoustic analyses for individual segments.
    • Waveform
    • Power Over Time and Power Over Frequency
    • Spectrogram and Formant Frequency Detection
    • Mel-Frequency Filter Bank and Mel-Frequency Cepstral Coefficients

Examples

Parse a recording and display speaker segment counts

Follow the normal process for importing data from the used LENA recorder to your LENA workstation. Use the LENA software export to save the ITS and WAV files.

From a terminal at the root of the speechvis library:

ipython -i speechvis.py

In the python interpreter:

root = <new root location>
ids.append(<new recording id>)
recording = Recording(root, ids[-1])
plot_speaker_counts(recording)

Display a Principal Components decomposition of the MFCCs for a speaker

In the python interpreter:

recording = Recording(root, ids[<Rec #>])
plot_mfcc_pca(recording, 'CHN') # Change CHN to any LENA speaker category

speechvis's People

Contributors

tim-shea avatar

Stargazers

 avatar

Watchers

 avatar  avatar

Forkers

anneswarlaumont

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.