BEA-Base: A Benchmark for ASR of Spontaneous Hungarian

Peter Mihajlik, Andras Balog, Tekla Etelka Graczi, Anna Kohari, Balázs Tarján, Katalin Mady

Abstract
Hungarian is spoken by 15 million people, still, easily accessible Automatic Speech Recognition (ASR) benchmark datasets – especially for spontaneous speech – have been practically unavailable. In this paper, we introduce BEA-Base, a subset of the BEA spoken Hungarian database comprising mostly spontaneous speech of 140 speakers. It is built specifically to assess ASR, primarily for conversational AI applications. After defining the speech recognition subsets and task, several baselines – including classic HMM-DNN hybrid and end-to-end approaches augmented by cross-language transfer learning – are developed using open-source toolkits. The best results obtained are based on multilingual self-supervised pretraining, achieving a 45% recognition error rate reduction as compared to the classical approach – without the application of an external language model or additional supervised data. The results show the feasibility of using BEA-Base for training and evaluation of Hungarian speech recognition systems.
Anthology ID:
2022.lrec-1.211
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:
1970–1977
Language:
URL:
https://aclanthology.org/2022.lrec-1.211
DOI:
Bibkey:
Cite (ACL):
Peter Mihajlik, Andras Balog, Tekla Etelka Graczi, Anna Kohari, Balázs Tarján, and Katalin Mady. 2022. BEA-Base: A Benchmark for ASR of Spontaneous Hungarian. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 1970–1977, Marseille, France. European Language Resources Association.
Cite (Informal):
BEA-Base: A Benchmark for ASR of Spontaneous Hungarian (Mihajlik et al., LREC 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/2022.lrec-1.211.pdf
Data
Common Voice
PDF Search