Gracias por enviar su consulta! Uno de los miembros de nuestro equipo se pondrá en contacto con usted en breve.
Gracias por enviar su reserva! Uno de los miembros de nuestro equipo se pondrá en contacto con usted en breve.
Programa del Curso
Foundations of Audio Classification
- Sound event types: environmental, mechanical, human-generated
- Overview of use cases: surveillance, monitoring, automation
- Audio classification vs detection vs segmentation
Audio Data and Feature Extraction
- Types of audio files and formats
- Sampling rate, windowing, frame size considerations
- Extracting MFCCs, chroma features, mel-spectrograms
Data Preparation and Annotation
- UrbanSound8K, ESC-50, and custom datasets
- Labeling sound events and temporal boundaries
- Balancing datasets and augmenting audio
Building Audio Classification Models
- Using convolutional neural networks (CNNs) for audio
- Model input: raw waveform vs features
- Loss functions, evaluation metrics, and overfitting
Event Detection and Temporal Localization
- Frame-based and segment-based detection strategies
- Post-processing detections using thresholds and smoothing
- Visualizing predictions on audio timelines
Advanced Topics and Real-Time Processing
- Transfer learning for low-data scenarios
- Deploying models with TensorFlow Lite or ONNX
- Streaming audio processing and latency considerations
Project Development and Application Scenarios
- Designing a full pipeline: ingestion to classification
- Developing a proof-of-concept for surveillance, quality control, or monitoring
- Logging, alerting, and integration with dashboards or APIs
Summary and Next Steps
Requerimientos
- An understanding of machine learning concepts and model training
- Experience with Python programming and data preprocessing
- Familiarity with digital audio fundamentals
Audience
- Data scientists
- Machine learning engineers
- Researchers and developers in audio signal processing
21 Horas
