Nkululeko: A Tool For Rapid Speaker Characteristics Detection

Felix Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben, Björn Schuller


Abstract
We present advancements with a software tool called Nkululeko, that lets users perform (semi-) supervised machine learning experiments in the speaker characteristics domain. It is based on audformat, a format for speech database metadata description. Due to an interface based on configurable templates, it supports best practise and very fast setup of experiments without the need to be proficient in the underlying language: Python. The paper explains the handling of Nkululeko and presents two typical experiments: comparing the expert acoustic features with artificial neural net embeddings for emotion classification and speaker age regression.
Anthology ID:
2022.lrec-1.205
Volume:
Proceedings of the Thirteenth Language Resources and Evaluation Conference
Month:
June
Year:
2022
Address:
Marseille, France
Editors:
Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
1925–1932
Language:
URL:
https://aclanthology.org/2022.lrec-1.205
DOI:
Bibkey:
Cite (ACL):
Felix Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben, and Björn Schuller. 2022. Nkululeko: A Tool For Rapid Speaker Characteristics Detection. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 1925–1932, Marseille, France. European Language Resources Association.
Cite (Informal):
Nkululeko: A Tool For Rapid Speaker Characteristics Detection (Burkhardt et al., LREC 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.lrec-1.205.pdf
Code
 felixbur/nkululeko