Listen, Attend, Spell and Adapt: Speaker Adapted Sequence-to-Sequence ASR

Jesús Andrés-Ferrer
Jesús Andrés-Ferrer
Xinwei Li
Xinwei Li
Puming Zhan
Puming Zhan

INTERSPEECH, pp. 3805-3809, 2019.

Cited by: 5|Bibtex|Views57|DOI:https://doi.org/10.21437/Interspeech.2019-2719
EI
Other Links: academic.microsoft.com|dblp.uni-trier.de|arxiv.org

Abstract:

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

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments