Multilingual intelligent assistants, such as ChatGPT, have recently gain...
Click-through rate (CTR) prediction is a crucial issue in recommendation...
Reduced-order models based on physics are a popular choice in cardiovasc...
In this paper, we study the problem of temporal video grounding (TVG), w...
Very deep models for speaker recognition (SR) have demonstrated remarkab...
Probabilistic linear discriminant analysis (PLDA) is commonly used in sp...
The CTC model has been widely applied to many application scenarios beca...
Recent advances of semantic image segmentation greatly benefit from deep...
State-of-art speaker verification (SV) systems use a back-end model to s...
Utilizing text-only data with an external language model (LM) in end-to-...
History and future contextual information are known to be important for
...
Limited computational budgets often prevent transformers from being used...
Speaker verification can be formulated as a representation learning task...
Some explanations to Kaldi's PLDA implementation to make formula derivat...
Benchmarking is key for developing and comparing optimization algorithms...