Von: Marc Voigt via ak discourse
Datum: Thu, 14 Apr 2022
Betreff: [ak-discourse] Einladung zum Forschungskolloquium am 19.04.2022
Liebe Kollegen und Studierende, liebe Interessenten an Veranstaltungen
am Fachgebiet Audiokommunikation,
am kommenden Dienstag, 19.04.2022, 16:00 Uhr s.t. (EN 324 / Zoom) tragen
Fabian Seipel und Corvin Jaedicke (ai|coustics) zum Thema „Speech
Enhancement with Deep Learning“ vor. Dazu möchten wir Sie sehr herzlich
einladen. Eine Kurzzusammenfassung darüber finden Sie, wie immer, am
Ende dieser E-Mail.
Aufgrund der aktuellen Gesundheitslage findet dieses
Forschungskolloquium als Hybridveranstaltung statt, hierfür nutzen wir
die Software Zoom in einer für die TU Berlin angepassten Version,
installieren sie dazu bitte die Client-Software für ihr System, die
ausführlichen Zugangsdaten finden sie nochmals am Ende dieser E-Mail.
Vor Ort gelten die Hygieneregeln der TU Berlin:
https://www.tu.berlin/themen/coronavirus/hygieneregeln/
Zoom-Meeting beitreten
https://tu-berlin.zoom.us/j/69049805599?pwd=L1U5QWpKN3BuUkRGaEpTVUF4ZG91UT09
Meeting-ID: 690 4980 5599
Kenncode: 20220419
Viele Grüße
Marc Voigt
—
Fabian Seipel und Corvin Jaedicke (ai|coustics): Speech Enhancement with
Deep Learning
Is it relevant how good a voice sounds? Yes! We as humans are able to
detect a variety of non-linguistic yet highly relevant information when
listening to a voice. We want to hear intelligible and pleasant-sounding
voices, and even more, we want our own voices to sound clear and
convincing to listeners. Even if people do not perceive voices as
consciously as for example faces in video calls – the voice is always
present and is also perceived unconsciously; in contrast to the video
feed, it is essential in online communication.
This is even more significant as our daily communication and media
consumption now takes place to an even greater extent in the digital
space: Online meetings, lectures, podcasts, school lessons, video
tutorials, voice messages, etc.; a trend that has been further amplified
by the digitalization of the workplace due to the Covid-19 pandemic.
However, the quality of audio is often deterred by various artifacts
such as background noise, inferior microphones, reverberant rooms, poor
internet connection and other disturbances. This reduces the
intelligibility, causes misunderstandings and concentration
difficulties, and ultimately diminishes the experience in online
meetings and media content.
ai|coustics is pioneering innovative audio algorithms based on AI and
deep learning models and fundamentally improving the capabilities of
speech audio enhancement in digital communication and media content.
—
Voigt, Marc lädt Sie zu einem geplanten Zoom-Meeting auf der TU Berlin
Zoom Instanz ein.
Thema: Forschungskolloquium
Uhrzeit: 19.Apr..2022 16:00 Amsterdam, Berlin, Rom, Stockholm, Wien
Zoom-Meeting beitreten
https://tu-berlin.zoom.us/j/69049805599?pwd=L1U5QWpKN3BuUkRGaEpTVUF4ZG91UT09
Meeting-ID: 690 4980 5599
Kenncode: 20220419
Schnelleinwahl mobil
+496971049922,,69049805599#,,,,,,0#,,20220419# Deutschland
+496950502596,,69049805599#,,,,,,0#,,20220419# Deutschland
Einwahl nach aktuellem Standort
+49 69 7104 9922 Deutschland
+49 695 050 2596 Deutschland
Meeting-ID: 690 4980 5599
Kenncode: 20220419
Ortseinwahl suchen: https://tu-berlin.zoom.us/u/cdmvk2kQ6y
Über SIP beitreten
sip:69049805599.20220419@fr.zmeu.us
Über H.323 beitreten
213.19.144.110 (Amsterdam
Niederlande)
213.244.140.110 (Deutschland)
Kenncode: 20220419
Meeting-ID: 690 4980 5599
…