Sorry, you need to enable JavaScript to visit this website.

Speech-to-text alignment is a critical component of neural text-to-speech (TTS) models. Autoregressive TTS models typically use an attention mechanism to learn these alignments on-line. However, these alignments tend to be brittle and often fail to generalize to long utterances and out-of-domain text, leading to missing or repeating words. Most non-autoregressive end-to-end TTS models rely on durations extracted from external sources. In this paper we leverage the alignment mechanism proposed in RAD-TTS and demonstrate its applicability to wide variety of neural TTS models.

The success of supervised deep learning heavily depends on large labeled datasets whose construction is often challenging in medical image analysis. Contrastive learning, a variant of self-supervised learning, is a potential solution to alleviate the strong demand for data annotation. In this work, we extend the contrastive learning framework to 3D volumetric medical imaging.

Aspect-Based Sentiment Analysis (ABSA) is a fine-grained sentiment analysis task and has become a significant task with real-world scenario value. The challenge of this task is how to generate an effective text representation and construct an end-to-end model that can simultaneously detect (target, aspect, sentiment) triples from a sentence. Besides, the existing models do not take the heavily unbalanced distribution of labels into account and also do not give enough consideration to long-distance dependence of targets and aspect-sentiment pairs.

Aspect-Based Sentiment Analysis (ABSA) is a fine-grained sentiment analysis task and has become a significant task with real-world scenario value. The challenge of this task is how to generate an effective text representation and construct an end-to-end model that can simultaneously detect (target, aspect, sentiment) triples from a sentence. Besides, the existing models do not take the heavily unbalanced distribution of labels into account and also do not give enough consideration to long-distance dependence of targets and aspect-sentiment pairs.

Few-shot object detection (FSOD) enables the detector to recognize novel objects only using limited training samples, which could greatly alleviate model’s dependency on data. Most existing methods include two training stages, namely base training and fine-tuning. However, the unlabeled novel instances in the base set were untouched in previous works, which can be re-used to enhance the FSOD performance. Thus, a new instance mining model is proposed in this paper to excavate the novel samples from the base set. The detector is thus fine-tuned again by these additional free novel instances.