Course unit, curriculum year 2023–2024
COMP.SGN.220
Advanced Audio Processing, 5 cr
Tampere University
- Description
- Completion options
Teaching periods
Active in period 3 (1.1.2024–3.3.2024)
Active in period 4 (4.3.2024–31.5.2024)
Active in period 5 (1.6.2024–31.7.2024)
Course code
COMP.SGN.220Language of instruction
EnglishAcademic years
2021–2022, 2022–2023, 2023–2024Level of study
Advanced studiesGrading scale
General scale, 0-5Persons responsible
Responsible teacher:
Tuomas VirtanenResponsible organisation
Faculty of Information Technology and Communication Sciences 100 %
Coordinating organisation
Computing Sciences Studies 100 %
Core content
- Acoustic feature extraction and audio classification. Automatic speech recognition. Use of temporal information in classification: hidden Markov models, recurrent neural networks, connectionist temporal classification, convolutional neural networks.
- Source separation (one channel and multichannel). Time-frequency masking. Deep neural network based and spectrogram factorization based source separation techniques.
- Microphone array signal processing: beamforming, source localization and tracking.
Learning outcomes
Prerequisites
Compulsory prerequisites
Further information
Learning material
Equivalences
Studies that include this course
Completion option 1
Accepted exercises, project work, and exam.
Completion of all options is required.
Participation in teaching
08.01.2024 – 27.02.2024
Active in period 3 (1.1.2024–3.3.2024)