# jameslyons/python_speech_features

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/jameslyons-python-speech-features).**

2,422 stars · 609 forks · Python · MIT

## Links

- GitHub: https://github.com/jameslyons/python_speech_features
- awesome-repositories: https://awesome-repositories.com/repository/jameslyons-python-speech-features.md

## Description

Python speech features is a signal processing toolkit and library for extracting standard speech recognition features from raw audio signals. It provides computational capabilities to calculate mel-frequency cepstral coefficients, raw and log filterbank energies, and spectral subband centroids for automated speech recognition systems and acoustic analysis.

The library implements audio signal transformations including pre-emphasis filtering, overlapping windowed frame segmentation, Fast Fourier Transform spectral analysis, mel-filterbank projection with configurable filter weights and frequency ranges, and discrete cosine transform cepstral projection.

## Tags

### Graphics & Multimedia

- [Audio Feature Extraction](https://awesome-repositories.com/f/graphics-multimedia/media-processing-analysis/media-manipulation/media-processing-workflows/audio-analysis-synthesis/audio-feature-extraction.md) — Computes standard audio representations such as mel-frequency cepstral coefficients and filterbank energies from raw audio. ([source](https://github.com/jameslyons/python_speech_features/blob/master/README.rst))
- [Mel-Frequency Cepstral Coefficients](https://awesome-repositories.com/f/graphics-multimedia/audio-music/audio-processing/real-time-analysis/audio-frequency-analysis/mel-frequency-cepstral-coefficients.md) — Applies a discrete cosine transform to convert log filterbank energies into cepstral coefficients.
- [Audio Frequency Analysis](https://awesome-repositories.com/f/graphics-multimedia/audio-music/audio-processing/real-time-analysis/audio-frequency-analysis.md) — Analyzes audio signals by computing spectral subband centroids to characterize frequency distributions.

### Artificial Intelligence & ML

- [Mel-band Energy Extractions](https://awesome-repositories.com/f/artificial-intelligence-ml/audio-processing/mel-spectrogram-processing/mel-band-energy-extractions.md) — Transforms audio frequency spectrums into perceptually-scaled filterbank energies using configurable mel-triangle filter weights.
- [Speech Recognition](https://awesome-repositories.com/f/artificial-intelligence-ml/speech-recognition.md) — Extracts standard audio representations like mel-frequency cepstral coefficients for speech recognition tasks.

### Part of an Awesome List

- [Feature Extraction](https://awesome-repositories.com/f/awesome-lists/ai/feature-extraction.md) — Provides a signal processing toolkit for computing cepstral coefficients and filterbank energies for speech recognition.
- [Spectral Centroids](https://awesome-repositories.com/f/awesome-lists/ai/feature-extraction/audio-spectral-features/spectral-centroids.md) — Computes spectral subband centroids from audio signals to characterize frequency distribution. ([source](https://github.com/jameslyons/python_speech_features#readme))

### Scientific & Mathematical Computing

- [Fourier Transforms](https://awesome-repositories.com/f/scientific-mathematical-computing/data-modeling-processing/signal-processing/fourier-transforms.md) — Converts windowed time-domain audio frames into frequency-domain power spectra using numerical Fourier transforms.
- [Pre-Emphasis Filters](https://awesome-repositories.com/f/scientific-mathematical-computing/signal-filtering-pipelines/pre-emphasis-filters.md) — Applies a high-pass digital filter to raw audio signals to amplify high frequencies.

### Data & Databases

- [Windowed Segmentation](https://awesome-repositories.com/f/data-databases/time-series-manipulation/windowed-segmentation.md) — Segments continuous audio waveforms into overlapping short-time frames using configurable window functions.