Environment Classification via Blind Roomprints Estimation

Environment Classification via Blind Roomprints Estimation

In this paper we present a novel approach for environment classification for speech recordings, which does not require the selection of decaying reverberation tails. It is based on a multi-band RT60 analysis of blind channel estimates and achieves an accuracy of up to 93.6% on test recordings derive...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-01
Hauptverfasser: Baum, Malte, Cuccovillo, Luca, Yaroshchuk, Artem, Aichroth, Patrick
Format: Artikel
Sprache:eng
Schlagworte:
Classification
Computer Science - Sound
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this paper we present a novel approach for environment classification for speech recordings, which does not require the selection of decaying reverberation tails. It is based on a multi-band RT60 analysis of blind channel estimates and achieves an accuracy of up to 93.6% on test recordings derived from the ACE corpus.
ISSN:2331-8422
DOI:10.48550/arxiv.2209.07196