UtterIdNet is a DNN that delivers consistent speaker recognition on VoxCeleb for segments down to 250 ms, with reported gains over prior models especially at sub-second lengths.
We evaluated our method using the V ox- Celeb datasets, and demonstrated that UtterIdNet outperforms the state-of-the-art for short segments
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Deep Neural Network for Short-Segment Speaker Recognition
UtterIdNet is a DNN that delivers consistent speaker recognition on VoxCeleb for segments down to 250 ms, with reported gains over prior models especially at sub-second lengths.