Deep Transformer based Data Augmentation with Subword Units for Morphologically Rich Online ASR
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 …
modeling tasks for ASR. Their high complexity, however, makes them very difficult to apply in …
Morphology aware data augmentation with neural language models for online hybrid ASR
Recognition of Hungarian conversational telephone speech is challenging due to the
informal style and morphological richness of the language. Neural Network Language …
informal style and morphological richness of the language. Neural Network Language …
Improving real-time recognition of morphologically rich speech with transformer language model
Transformer models have become to state-of-the-art in natural language understanding,
their use for language modeling in Automatic Speech Recognition (ASR) is also promising …
their use for language modeling in Automatic Speech Recognition (ASR) is also promising …
On the effectiveness of neural text generation based data augmentation for recognition of morphologically rich speech
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 …
recent years, however, in language modeling many systems still rely on traditional Back-off …
Language Modeling for Hungarian Speech Recognition
B Tarján - 2021 - search.proquest.com
Automatic speech recognition (ASR) systems enable the machine transcription of human
speech. Language model plays an important role in ASR systems, as the final automatic …
speech. Language model plays an important role in ASR systems, as the final automatic …