The goal of this work is to reconstruct high quality speech from lip mot...
While recent text-to-speech (TTS) systems have made remarkable strides t...
Question Answering (QA) is a task that entails reasoning over natural
la...
K-nearest neighbor search is one of the fundamental tasks in various
app...
The retriever-reader pipeline has shown promising performance in open-do...
In Neural Architecture Search (NAS), reducing the cost of architecture
e...
Few-shot speaker adaptation is a specific Text-to-Speech (TTS) system th...
In multi-hop QA, answering complex questions entails iterative document
...
Although recent works on neural vocoder have improved the quality of
syn...
Extractive QA models have shown very promising performance in predicting...
To mitigate the pain of manually tuning hyperparameters of deep neural
n...
Many hyperparameter optimization (HyperOpt) methods assume restricted
co...