Lecture: Audio Processing for the Internet of Things (AIoT) (Summer Term 2022)

  • Instructor: Prof. Dr. Nils Peters

  • Credits: 2.5 ECTS

  • Format: Lecture, in English

  • Term: Summer 2022

  • Time: Tuesday 14:15 - 15:45 (1st Lecture: 26.04.2022)

  • Location: Via ZOOM. Link and access information for ZOOM meetings can be found at StudOn (see below).

  • Dates: Tue 26.4.2022, Tue 3.5.2022, Tue 10.5.2022, Tue 17.5.2022, Tue 24.5.2022, Tue 31.5.2022, Tue 7.6.2022, Tue 14.6.2022, Tue 21.6.2022, Tue 28.6.2022, Tue 5.7.2022, Tue 12.7.2022, Tue 19.7.2022

  • Office Hours: Wed 13:00–14:00 (virtual, use lecture ZOOM link)

  • Exam (graded): Oral examination at the end of term.

  • Examination Dates and Location: To be announced, subject to COVID-19 safety regulations.

Important Notes:
  • Due to the COVID-19 pandemic, the lecture Audio Processing for the Internet of Things will be offered as a fully virtual course via ZOOM.
  • Participation in the ZOOM sessions is only possible for FAU students. To access the Zoom sessions, you must register via StudOn prior to the first lecture. In StudOn, you will then find Zoom access information.
  • As a technical requirement, all participants must have access to a computer capable of running the ZOOM video conferencing software, including a stable internet connection for audio and video transmission.

Content

The course focuses on audio and speech processing algorithms within the context of the Internet of Things (IoT). Reading material recommendations are provided during the lectures.

  • Foundation: history, components, current challenges
  • Overview of Relevant Wireless Protocols: bandwidth, range, latency, spectrum
  • Audio Device Synchronization: NTP, PTP, device orchestration, wireless acoustic sensor networks, asynchronous and event-driven audio sampling
  • Acoustic Sensing for Voice User Interfaces: keyword spotting, speech recognition, speaker verification, anti-spoofing
  • Acoustic Scene Detection: event detection, scene classification, anomaly detection, sound tagging, blind reverb estimation
  • Sound Creation: text-to-speech, sound generative networks
  • Data-over-sound: sound-beacon, watermarking, acoustic fingerprint
  • Privacy in IoT: edge vs. cloud processing, secure signal processing, federated learning, differential privacy, audio encryption

Course Requirements

Before starting this lecture, it is recommended to complete the following FAU courses (or have equivalent knowledge):

  • Signals and Systems I & II
  • Digital Signal Processing
  • Deep Learning, Machine Learning in Signal Processing

Links