Login / Signup
T-vectors: Weakly Supervised Speaker Identification Using Hierarchical Transformer Model.
Yanpei Shi
Mingjie Chen
Qiang Huang
Thomas Hain
Published in:
CoRR (2020)
Keyphrases
</>
high level
weakly supervised
information retrieval
image sequences
probabilistic model
speaker identification
feature vectors
prior knowledge
graph cuts
model selection