Related papers: Advancing Semi-Supervised Learning for Automatic P…

We propose a new strategy to improve the accuracy and robustness of image classification. First, we train a baseline CNN model. Then, we identify challenging regions in the feature space by identifying all misclassified samples, and…

In this paper, we introduce a novel approach to generate synthetic data for training Neural Machine Translation systems. The proposed approach transforms a given parallel corpus between a written language and a target language to a parallel…

Inspite the emerging importance of Speech Emotion Recognition (SER), the state-of-the-art accuracy is quite low and needs improvement to make commercial applications of SER viable. A key underlying reason for the low accuracy is the…

Imbalanced data, where the positive samples represent only a small proportion compared to the negative samples, makes it challenging for classification problems to balance the false positive and false negative rates. A common approach to…

We present Adjacent Possible Exploration (APE), a selective fine-tuning method for adapting large language models that systematically explores parameter modifications while maintaining model stability. Inspired by evolutionary optimization…

Despite the growing interest in unsupervised learning, extracting meaningful knowledge from unlabelled audio remains an open challenge. To take a step in this direction, we recently proposed a problem-agnostic speech encoder (PASE), that…

As machine learning models continue to swiftly advance, calibrating their performance has become a major concern prior to practical and widespread implementation. Most existing calibration methods often negatively impact model accuracy due…

We introduce unsupervised techniques based on phrase-based statistical machine translation for grammatical error correction (GEC) trained on a pseudo learner corpus created by Google Translation. We verified our GEC system through…

Synthetic data has been proposed as a solution to address the issue of high-quality data scarcity in the training of large language models (LLMs). Studies have shown that synthetic data can effectively improve the performance of LLMs on…

AI-synthesized speech, also known as deepfake speech, has recently raised significant concerns due to the rapid advancement of speech synthesis and speech conversion techniques. Previous works often rely on distinguishing synthesizer…

We study the problem of generating keyphrases that summarize the key points for a given document. While sequence-to-sequence (seq2seq) models have achieved remarkable performance on this task (Meng et al., 2017), model training often relies…

Speech representation learning has improved both speech understanding and speech synthesis tasks for single language. However, its ability in cross-lingual scenarios has not been explored. In this paper, we extend the pretraining method for…

In Natural Language Generation (NLG), End-to-End (E2E) systems trained through deep learning have recently gained a strong interest. Such deep models need a large amount of carefully annotated data to reach satisfactory performance.…

This paper explores augmenting monolingual data for knowledge distillation in neural machine translation. Source language monolingual text can be incorporated as a forward translation. Interestingly, we find the best way to incorporate…

Scene Parsing is a crucial step to enable autonomous systems to understand and interact with their surroundings. Supervised deep learning methods have made great progress in solving scene parsing problems, however, come at the cost of…

Recent advancements in end-to-end speech synthesis have made it possible to generate highly natural speech. However, training these models typically requires a large amount of high-fidelity speech data, and for unseen texts, the prosody of…

Leveraging deep learning models for Anomaly Detection (AD) has seen widespread use in recent years due to superior performances over traditional methods. Recent deep methods for anomalies in images learn better features of normality in an…

Automatic post-editing (APE) aims to correct errors in machine-translated text, enhancing translation quality, while reducing the need for human intervention. Despite advances in neural machine translation (NMT), the development of…

Existing models of multilingual sentence embeddings require large parallel data resources which are not available for low-resource languages. We propose a novel unsupervised method to derive multilingual sentence embeddings relying only on…

The availability of parallel texts is crucial to the performance of machine translation models. However, most of the world's languages face the predominant challenge of data scarcity. In this paper, we propose strategies to synthesize…