BEA-Base: A Benchmark for ASR of Spontaneous Hungarian
Péter Mihajlik, A. Balog, T. E. Gráczi, Anna Kohári, Balázs Tarján, K. Mády · 2022
Hungarian is spoken by 15 million people, still, easily accessible Automatic Speech Recognition (ASR) benchmark datasetsespecially for spontaneous speechhave 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 baselinesincluding classic HMM-DNN hybrid and end-to-end approaches augmented by cross-language transfer learningare 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 approachwithout 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.