Listen, Attend, Spell and Adapt: Speaker Adapted Sequence-to-Sequence ASR
INTERSPEECH, pp. 3805-3809, 2019.
Sequence-to-sequence (seq2seq) based ASR systems have shown state-of-the-art performances while having clear advantages in terms of simplicity. However, comparisons are mostly done on speaker independent (SI) ASR systems, though speaker adapted conventional systems are commonly used in practice for improving robustness to speaker and en...More
PPT (Upload PPT)