Librosa: Difference between revisions
mNo edit summary |
mNo edit summary |
||
| Line 5: | Line 5: | ||
librosa | librosa | ||
librosa.beat | = librosa.beat = | ||
Functions for estimating tempo and detecting beat events. | Functions for estimating tempo and detecting beat events. | ||
librosa.core | = librosa.core = | ||
Core functionality includes functions to load audio from disk, compute various spectrogram representations, and a variety of commonly used tools for music analysis. For convenience, all functionality in this submodule is directly accessible from the top-level librosa.* namespace. | Core functionality includes functions to load audio from disk, compute various spectrogram representations, and a variety of commonly used tools for music analysis. For convenience, all functionality in this submodule is directly accessible from the top-level librosa.* namespace. | ||
librosa.decompose | = librosa.decompose = | ||
Functions for harmonic-percussive source separation (HPSS) and generic spectrogram decomposition using matrix decomposition methods implemented in scikit-learn. | Functions for harmonic-percussive source separation (HPSS) and generic spectrogram decomposition using matrix decomposition methods implemented in scikit-learn. | ||
librosa.display | = librosa.display = | ||
Visualization and display routines using matplotlib. | Visualization and display routines using matplotlib. | ||
librosa.effects | = librosa.effects = | ||
Time-domain audio processing, such as pitch shifting and time stretching. This submodule also provides time-domain wrappers for the decompose submodule. | Time-domain audio processing, such as pitch shifting and time stretching. This submodule also provides time-domain wrappers for the decompose submodule. | ||
librosa.feature | = librosa.feature = | ||
Feature extraction and manipulation. This includes low-level feature extraction, such as chromagrams, Mel spectrogram, MFCC, and various other spectral and rhythmic features. Also provided are feature manipulation methods, such as delta features and memory embedding. | Feature extraction and manipulation. This includes low-level feature extraction, such as chromagrams, Mel spectrogram, MFCC, and various other spectral and rhythmic features. Also provided are feature manipulation methods, such as delta features and memory embedding. | ||
librosa.filters | = librosa.filters = | ||
Filter-bank generation (chroma, pseudo-CQT, CQT, etc.). These are primarily internal functions used by other parts of librosa. | Filter-bank generation (chroma, pseudo-CQT, CQT, etc.). These are primarily internal functions used by other parts of librosa. | ||
librosa.onset | = librosa.onset = | ||
Onset detection and onset strength computation. | Onset detection and onset strength computation. | ||
librosa.segment | = librosa.segment = | ||
Functions useful for structural segmentation, such as recurrence matrix construction, time-lag representation, and sequentially constrained clustering. | Functions useful for structural segmentation, such as recurrence matrix construction, time-lag representation, and sequentially constrained clustering. | ||
librosa.sequence | = librosa.sequence = | ||
Functions for sequential modeling. Various forms of Viterbi decoding, and helper functions for constructing transition matrices. | Functions for sequential modeling. Various forms of Viterbi decoding, and helper functions for constructing transition matrices. | ||
librosa.util | = librosa.util = | ||
Helper utilities (normalization, padding, centering, etc.) | Helper utilities (normalization, padding, centering, etc.) | ||
Revision as of 20:33, 25 August 2021
Python library used for audio manipulation especially uselful with Deep Learning
The librosa package is structured as collection of submodules:
librosa
librosa.beat[edit]
Functions for estimating tempo and detecting beat events.
librosa.core[edit]
Core functionality includes functions to load audio from disk, compute various spectrogram representations, and a variety of commonly used tools for music analysis. For convenience, all functionality in this submodule is directly accessible from the top-level librosa.* namespace.
librosa.decompose[edit]
Functions for harmonic-percussive source separation (HPSS) and generic spectrogram decomposition using matrix decomposition methods implemented in scikit-learn.
librosa.display[edit]
Visualization and display routines using matplotlib.
librosa.effects[edit]
Time-domain audio processing, such as pitch shifting and time stretching. This submodule also provides time-domain wrappers for the decompose submodule.
librosa.feature[edit]
Feature extraction and manipulation. This includes low-level feature extraction, such as chromagrams, Mel spectrogram, MFCC, and various other spectral and rhythmic features. Also provided are feature manipulation methods, such as delta features and memory embedding.
librosa.filters[edit]
Filter-bank generation (chroma, pseudo-CQT, CQT, etc.). These are primarily internal functions used by other parts of librosa.
librosa.onset[edit]
Onset detection and onset strength computation.
librosa.segment[edit]
Functions useful for structural segmentation, such as recurrence matrix construction, time-lag representation, and sequentially constrained clustering.
librosa.sequence[edit]
Functions for sequential modeling. Various forms of Viterbi decoding, and helper functions for constructing transition matrices.
librosa.util[edit]
Helper utilities (normalization, padding, centering, etc.)