IL-ho Yang
3 papers · 2017–2019 · 1 venue · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(11)
🐣
Hot Topic Early Bird
Venues
Research topics
Keywords
speaker embedding
(2)
speaker verification
(2)
regularization technique
(1)
end-to-end learning
(1)
end-to-end training
(1)
joint training
(1)
hard negative mining
(1)
raw waveform
(1)
speaker overfitting
(1)
text-independent speaker verification
(1)
neural network
(1)
end-to-end loss
(1)
metric learning
(1)
end-to-end deep neural network
(1)
deep neural network
(1)
Papers
End-to-End Losses Based on Speaker Basis Vectors and All-Speaker Hard Negative Mining for Speaker Verification
Interspeech 2019
Avoiding Speaker Overfitting in End-to-End DNNs Using Raw Waveform for Text-Independent Speaker Verification
Interspeech 2018
Joint Training of Expanded End-to-End DNN for Text-Dependent Speaker Verification
Interspeech 2017