Improving End-to-end Speech Recognition with Pronunciation-assisted Sub-word Modeling
Improving End-to-end Speech Recognition with Pronunciation-assisted Sub-word Modeling
Most end-to-end speech recognition systems model text directly as a sequence of characters or sub-words. Current approaches to sub-word extraction only consider character sequence frequencies, which at times produce inferior sub-word segmentation that might lead to erroneous speech recognition output. We propose pronunciation-assisted sub-word modeling (PASM), a sub-word extraction method …