Related papers: Token-Level Supervised Contrastive Learning for Pu…

Although automatic speech recognition (ASR) task has gained remarkable success by sequence-to-sequence models, there are two main mismatches between its training and testing that might lead to performance degradation: 1) The typically used…

Self-supervised learning has gained popularity because of its ability to avoid the cost of annotating large-scale datasets. It is capable of adopting self-defined pseudo labels as supervision and use the learned representations for several…

End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream in a single neural network. However, compared to conventional ASR systems, these…

Contrastive learning has been widely used to train transformer-based vision-language models for video-text alignment and multi-modal representation learning. This paper presents a new algorithm called Token-Aware Cascade contrastive…

Rapid progress in 3D semantic segmentation is inseparable from the advances of deep network models, which highly rely on large-scale annotated data for training. To address the high cost and challenges of 3D point-level labeling, we present…

Contrastive learning (CL) has achieved astonishing progress in computer vision, speech, and natural language processing fields recently with self-supervised learning. However, CL approach to the supervised setting is not fully explored,…

In recent years, the field of intelligent transportation systems (ITS) has achieved remarkable success, which is mainly due to the large amount of available annotation data. However, obtaining these annotated data has to afford expensive…

State-of-the-art speaker verification systems are inherently dependent on some kind of human supervision as they are trained on massive amounts of labeled data. However, manually annotating utterances is slow, expensive and not scalable to…

Contrastive learning applied to self-supervised representation learning has seen a resurgence in recent years, leading to state of the art performance in the unsupervised training of deep image models. Modern batch contrastive approaches…

Contrastive learning models have achieved great success in unsupervised visual representation learning, which maximize the similarities between feature representations of different views of the same image, while minimize the similarities…

Gradient-based adversarial training is widely used in improving the robustness of neural networks, while it cannot be easily adapted to natural language processing tasks since the embedding space is discrete. In natural language processing…

The next token prediction loss is the dominant self-supervised training objective for large language models and has achieved promising results in a variety of downstream tasks. However, upon closer investigation of this objective, we find…

State-of-the-art natural language understanding classification models follow two-stages: pre-training a large language model on an auxiliary task, and then fine-tuning the model on a task-specific labeled dataset using cross-entropy loss.…

Contrastive learning has gained popularity and pushes state-of-the-art performance across numerous large-scale benchmarks. In contrastive learning, the contrastive loss function plays a pivotal role in discerning similarities between…

To improve performance in visual feature representation from photos or videos for practical applications, we generally require large-scale human-annotated labeled data while training deep neural networks. However, the cost of gathering and…

Query spelling correction is an important function of modern search engines since it effectively helps users express their intentions clearly. With the growing popularity of speech search driven by Automated Speech Recognition (ASR)…

The goal of self-supervised learning (SSL) for automatic speech recognition (ASR) is to learn good speech representations from a large amount of unlabeled speech for the downstream ASR task. However, most SSL frameworks do not consider…

Since the meaning representations are detailed and accurate annotations which express fine-grained sequence-level semtantics, it is usually hard to train discriminative semantic parsers via Maximum Likelihood Estimation (MLE) in an…

Punctuation restoration is an important post-processing step in automatic speech recognition. Among other kinds of external information, part-of-speech (POS) taggers provide informative tags, suggesting each input token's syntactic role,…

Medical contrastive vision-language pre-training (VLP) has demonstrated significant potential in improving performance on downstream tasks. Traditional approaches typically employ contrastive learning, treating paired image-report samples…