2 citations · 2 across the 1 of their papers we have counts for
4 papers
BEA-Base: A Benchmark for ASR of Spontaneous Hungarian
P. Mihajlik, A. Balog, T. E. Gráczi +3
Hungarian is spoken by 15 million people, still, easily accessible Automatic Speech Recognition (ASR) benchmark datasets - especially for spontaneous speech - have been practically…
Deep Transformer based Data Augmentation with Subword Units for Morphologically Rich Online ASR
Balázs Tarján, György Szaszák, Tibor Fegyó +1
Recently Deep Transformer models have proven to be particularly powerful in language modeling tasks for ASR. Their high complexity, however, makes them very difficult to apply in t…
On the Effectiveness of Neural Text Generation based Data Augmentation for Recognition of Morphologically Rich Speech
Balázs Tarján, György Szaszák, Tibor Fegyó +1
Advanced neural network models have penetrated Automatic Speech Recognition (ASR) in recent years, however, in language modeling many systems still rely on traditional Back-off N-g…
Investigation on N-gram Approximated RNNLMs for Recognition of Morphologically Rich Speech
Balázs Tarján, György Szaszák, Tibor Fegyó +1
Recognition of Hungarian conversational telephone speech is challenging due to the informal style and morphological richness of the language. Recurrent Neural Network Language Mode…