Speech Enhancement (SpEn)2.5 ECTS
(englische Bezeichnung: Speech Enhancement)
(Prüfungsordnungsmodul: Speech Enhancement)

Lehrveranstaltungen:

• • Speech Enhancement
    (Vorlesung, 2 SWS, Emanuël A. P. Habets, Do, 8:15 - 9:45, Zoom-Meeting)

Empfohlene Voraussetzungen:

Es wird empfohlen, folgende Module zu absolvieren, bevor dieses Modul belegt wird:

Sprach- und Audiosignalverarbeitung (SS 2020)
Digitale Signalverarbeitung (WS 2019/2020)
Statistische Signalverarbeitung (WS 2019/2020)

Inhalt:

Course Description
We live in a noisy world! In all applications that are related to speech from hands-free communication, teleconferencing, hearing aids, cochlear implants, to human-machine interfaces such as smart speakers, a speech signal of interest captured by one or more microphones is contaminated by noise and reverberation. Depending on the level of noise and reverberation, the quality and intelligibility of the captured speech can be greatly reduced. Therefore, it is highly desirable, and sometimes even indispensable, to "clean up" the noisy signals using signal processing techniques before storage, transmission or reproduction.

In this course both traditional and deep learning methods for noise reduction and dereverberation, with one or more microphones, are discussed.

The goal of this course is to provide a strong foundation for researchers, engineers, and graduate students who are interested in the problem of signal and speech enhancement.

Relation to other courses
This course is the most advanced course offered by the university on this topic, and serves as an excellent basis from which to commence research in the area. Various aspects of the course bring students up to date with the very latest developments in the field, as seen in recent international conferences and journals. This course builds on Sprach- und Audiosignalverarbeitung (by Prof. Kellermann), and is well complimented by Selected Topics in Perceptual Audio Coding (Prof. Herre) and Auditory Models (Prof. Edler).

Lernziele und Kompetenzen:

Students

• Formulate the speech enhancement problem mathematically.

• Derive optimal single- and multi-channel filters to reduce noise and reverberation.

• Evaluate and compare the performance of single- and multi-channel filters for speech enhancement.

• Understand how reference signals and other prior information can be used in a speech enhancement system.

• Understand the limitations and challenges of existing speech enhancement systems.

• Understand the importance of binaural cues and the influence of a speech enhancement system on the binaural cues in the context of hearing aids.

• Design a microphone array and analyze its performance.

• Design a speech enhancement system for a given acoustic scenario.

• Evaluate both subjectively and objectively the performance of a speech enhancement system in terms of the speech quality and intelligibility.

Organisatorisches:

Die Unterrichts- und Prüfungssprache (Deutsch oder Englisch) wird in der ersten Lehrveranstaltung mit den Studierenden vereinbart.

Weitere Informationen:

Verwendbarkeit des Moduls / Einpassung in den Musterstudienplan:

1. Berufspädagogik Technik (Master of Education)
   (Po-Vers. 2020w | TechFak | Berufspädagogik Technik (Master of Education) | Gesamtkonto | Wahlpflichtmodule Fachwissenschaft | Speech Enhancement)

Studien-/Prüfungsleistungen:

Speech Enhancement (Prüfungsnummer: 68801)

(englischer Titel: Speech Enhancement)

Prüfungsleistung, mündliche Prüfung, Dauer (in Minuten): 30, benotet

Anteil an der Berechnung der Modulnote: 100.0 %

weitere Erläuterungen:
Die Prüfung kann wahlweise in Deutsch oder Englisch abgelegt werden.

Prüfungssprache: Deutsch oder Englisch

Erstablegung: WS 2020/2021, 1. Wdh.: SS 2021

1. Prüfer:

Emanuël A. P. Habets