C
search
search
reviewers
reviewers
feeds
feeds
assignments
assignments
settings
logout
Minimum Bayes Risk Training for End-to-End Speaker-Attributed ASR.
Naoyuki Kanda
Zhong Meng
Liang Lu
Yashesh Gaur
Xiaofei Wang
Zhuo Chen
Takuya Yoshioka
Published in:
ICASSP (2021)
Keyphrases
</>
end to end
bayes risk
automatic speech recognition
speech recognition
upper and lower bounds
loss function
training set
congestion control
supervised learning
reproducing kernel hilbert space
posterior probability
speech signal
regularization parameter
vector quantizer
special case
squared error
multiscale