Computer Audition - Notes¶

Overview¶

Computer Audition (CA) core concepts for real-world applications.

Roadmap¶

computer-audition/
│
├── Audio Processing
│   ├── Acoustic Signal Processing
│   │   ├── Noise Reduction
│   │   ├── Feature Extraction
│   │   └── Audio Enhancement
│   └── Source Separation
│       ├── Blind Source Separation
│       └── Beamforming
│
├── Audio Recognition
│   ├── Sound Recognition
│   │   ├── Sound Event Detection and Classification
│   │   ├── Audio Tagging (multi-label classification)
│   │   └── Environmental Sound Classification
│   ├── Speech-Related Tasks
│   │   ├── Automatic Speech Recognition (ASR)
│   │   ├── Speech Command Recognition (SCR)
│   │   ├── Speaker Recognition
│   │   └── Speech Emotion Recognition (SER)
│   ├── Music Information Retrieval
│   │   ├── Music Genre Classification
│   │   ├── Instrument Recognition
│   │   └── Music Mood/Emotion Classification
│   └── Acoustic Scene Classification (ASC)
│
├── Auditory Scene Analysis
│   ├── Scene Segmentation
│   └── Understanding soundscapes and context
│
├── Spatial Audio Analysis
│   ├── Sound Source Localization and Tracking
│   └── Spatial Parameter Estimation (e.g., room size)
│
├── Audio Captioning
│   └── Generating textual descriptions of audio scenes
│
├── Audio Question Answering
│   └── Answering queries about audio content
│
└── Related/Supporting Fields
    ├── Machine Listening
    ├── Computational Auditory Scene Analysis (CASA)
    └── Environmental Parameter Estimation

Contributing¶

Please refer to CONTRIBUTING.md file.

“Mr. Watson — Come here — I want to see you.¶

[First intelligible words spoken over the telephone]” ― Alexander Graham Bell