t-SOT FNT: Streaming Multi-talker ASR with Text-only Domain Adaptation Capability.

Jian Wu Naoyuki Kanda Takuya Yoshioka Rui Zhao Zhuo Chen Jinyu Li

Published in: CoRR (2023)

Keyphrases

domain adaptation
concept space
cross domain
multiple sources
transfer learning
labeled data
sentiment classification
target domain
text mining
semi supervised
document classification
web documents
test data
speech recognition
database
data streams
information retrieval
co training
unlabeled data
pairwise
keywords