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

Felix Weninger Jesús Andrés-Ferrer Xinwei Li Puming Zhan

Published in: INTERSPEECH (2019)

Keyphrases

speech recognition
automatic speech recognition
database
neural network
machine learning
information retrieval
computer vision
case study
sequence alignment
pseudorandom
sequence analysis