Related papers: Efficient CTC Regularization via Coarse Labels for…

Current continuous sign language recognition (CSLR) methods struggle with handling diverse samples. Although dynamic convolutions are ideal for this task, they mainly focus on spatial modeling and fail to capture the temporal dynamics and…

This paper presents an effective transfer learning framework for language adaptation in text-to-speech systems, with a focus on achieving language adaptation using minimal labeled and unlabeled data. While many works focus on reducing the…

Labeled data is a fundamental component in training supervised deep learning models for computer vision tasks. However, the labeling process, especially for ordinal image classification where class boundaries are often ambiguous, is prone…

We propose a novel regularizer for supervised learning called Conditioning on Noisy Targets (CNT). This approach consists in conditioning the model on a noisy version of the target(s) (e.g., actions in imitation learning or labels in…

Indias linguistic diversity poses significant challenges for developing inclusive Automatic Speech Recognition (ASR) systems. Traditional multilingual models, which require simultaneous access to all language data, are impractical due to…

End-to-end models that condition the output label sequence on all previously predicted labels have emerged as popular alternatives to conventional systems for automatic speech recognition (ASR). Since unique label histories correspond to…

Large pre-trained sentence encoders like BERT start a new chapter in natural language processing. A common practice to apply pre-trained BERT to sequence classification tasks (e.g., classification of sentences or sentence pairs) is by…

There is a family of label modification approaches including self and non-self label correction (LC), and output regularisation. They are widely used for training robust deep neural networks (DNNs), but have not been mathematically and…

We propose an end-to-end speech synthesizer, Fast DCTTS, that synthesizes speech in real time on a single CPU thread. The proposed model is composed of a carefully-tuned lightweight network designed by applying multiple network reduction…

Neural end-to-end TTS can generate very high-quality synthesized speech, and even close to human recording within similar domain text. However, it performs unsatisfactory when scaling it to challenging test sets. One concern is that the…

Visual-language foundation models, like CLIP, learn generalized representations that enable zero-shot open-set classification. Few-shot adaptation methods, based on prompt tuning, have been shown to further improve performance on downstream…

Recent advances in domain adaptation show that deep self-training presents a powerful means for unsupervised domain adaptation. These methods often involve an iterative process of predicting on target domain and then taking the confident…

Learning with noisy labels is an important and challenging task for training accurate deep neural networks. Some commonly-used loss functions, such as Cross Entropy (CE), suffer from severe overfitting to noisy labels. Robust loss functions…

Label smoothing has been shown to be an effective regularization strategy in classification, that prevents overfitting and helps in label de-noising. However, extending such methods directly to seq2seq settings, such as Machine Translation,…

This paper explores semi-supervised training for sequence tasks, such as Optical Character Recognition or Automatic Speech Recognition. We propose a novel loss function $\unicode{x2013}$ SoftCTC $\unicode{x2013}$ which is an extension of…

We consider the problem of localizing and segmenting individual teeth inside 3D Cone-Beam Computed Tomography (CBCT) images. To handle large image sizes we approach this task with a coarse-to-fine framework, where the whole volume is first…

With the development of deep learning, medical image classification has been significantly improved. However, deep learning requires massive data with labels. While labeling the samples by human experts is expensive and time-consuming,…

Pre-trained contextual language models such as BERT, GPT, and XLnet work quite well for document retrieval tasks. Such models are fine-tuned based on the query-document/query-passage level relevance labels to capture the ranking signals.…

In recent years, end-to-end speech recognition has emerged as a technology that integrates the acoustic, pronunciation dictionary, and language model components of the traditional Automatic Speech Recognition model. It is possible to…

Traditional methods for learning with the presence of noisy labels have successfully handled datasets with artificially injected noise but still fall short of adequately handling real-world noise. With the increasing use of meta-learning in…