Multilingual training is effective in improving low-resource ASR, which ...
We improve low-resource ASR by integrating the ideas of multilingual tra...
Recent studies have shown that using an external Language Model (LM) ben...
With the increasing popularity of speech synthesis products, the industr...
Recently Graph Neural Network (GNN) has been applied successfully to var...
Representation learning for speech emotion recognition is challenging du...
Interpretable multi-hop reading comprehension (RC) over multiple documen...
Multiple instance learning (MIL) aims to learn the mapping between a bag...
Multi-hop reading comprehension (RC) across documents poses new challeng...
The I4U consortium was established to facilitate a joint entry to NIST
s...
Speech emotion recognition (SER) has attracted great attention in recent...
Automatic pronunciation evaluation plays an important role in pronunciat...
Acoustic-prosodic entrainment describes the tendency of humans to align ...
Deep neural networks are typically represented by a much larger number o...