Pretrained Language Models (PLMs) have emerged as the state-of-the-art
p...
Using a text description as prompt to guide the generation of text or im...
Binaural audio plays a significant role in constructing immersive augmen...
Sentence scoring aims at measuring the likelihood score of a sentence an...
Text to speech (TTS) has made rapid progress in both academia and indust...
In the development of neural text-to-speech systems, model pre-training ...
Weight sharing has become the de facto approach to reduce the
training c...
Error correction techniques have been used to refine the output sentence...
Mean opinion score (MOS) is a popular subjective metric to assess the qu...
Multilingual neural machine translation (NMT) has recently been investig...
We Microsoft Research Asia made submissions to 11 language directions in...
Unsupervised neural machine translation (NMT) has attracted a lot of
att...