Research
Advancing how machines understand and generate human language across speech, text, and translation.
We are working on neural network based text to speech (TTS). including acoustic model, vocoder, frontend, and end-to-end text-to-wave model. Our research works have been transferred in Microsoft Azure TTS service to improve the product…
Uncertainty-aware self-training (UST) for few-shot text classification with pre-trained language models. With only 20-30 labeled samples per class for each task, UST can perform similar to fully supervised pre-trained language models like BERT fine-tuned on…