Related papers: Selective Augmentation: Improving Universal Automa…

Phoneme recognition is a largely unsolved problem in NLP, especially for low-resource languages like Urdu. The systems that try to extract the phonemes from audio speech require hand-labeled phonetic transcriptions. This requires expert…

Data augmentation is a key tool for improving the performance of deep networks, particularly when there is limited labeled data. In some fields, such as computer vision, augmentation methods have been extensively studied; however, for…

Automated Scoring (AS), the natural language processing task of scoring essays and speeches in an educational testing setting, is growing in popularity and being deployed across contexts from government examinations to companies providing…

Despite recent advancements in Machine Learning, many tasks still involve working in low-data regimes which can make solving natural language problems difficult. Recently, a number of text augmentation techniques have emerged in the field…

Pre-trained Vision-Language Models (VLMs) have recently shown promise in detecting anomalies. However, previous approaches are fundamentally limited by their reliance on human-designed prompts and the lack of accessible anomaly samples,…

Pre-trained Transformer-based speech models have shown striking performance when fine-tuned on various downstream tasks such as automatic speech recognition and spoken language identification (SLID). However, the problem of domain mismatch…

Speech Emotion Recognition (SER) is a crucial component in developing general-purpose AI agents capable of natural human-computer interaction. However, building robust multilingual SER systems remains challenging due to the scarcity of…

Understanding the internal representations of large language models is crucial for ensuring their reliability and safety, with sparse autoencoders (SAEs) emerging as a promising interpretability approach. However, current SAE training…

Practical sequence classification tasks in natural language processing often suffer from low training data availability for target classes. Recent works towards mitigating this problem have focused on transfer learning using embeddings…

Automatic speech recognition (ASR) research has achieved impressive performance in recent years and has significant potential for enabling access for people with dysarthria (PwD) in augmentative and alternative communication (AAC) and home…

Recent advances in synthetic speech quality have enabled us to train text-to-speech (TTS) systems by using synthetic corpora. However, merely increasing the amount of synthetic data is not always advantageous for improving training…

Self-Taught Reasoners (STaR), synonymously known as Rejection sampling Fine-Tuning (RFT), is an integral part of the training pipeline of self-improving reasoning Language Models (LMs). The self-improving mechanism often employs random…

Aspect-based sentiment analysis (ABSA) involves identifying sentiment towards specific aspect terms in a sentence and allows us to uncover nuanced perspectives and attitudes on particular aspects of a product, service, or topic. However,…

Recent studies on semi-supervised semantic segmentation (SSS) have seen fast progress. Despite their promising performance, current state-of-the-art methods tend to increasingly complex designs at the cost of introducing more network…

How can one perform Bayesian inference on stochastic simulators with intractable likelihoods? A recent approach is to learn the posterior from adaptively proposed simulations using neural network-based conditional density estimators.…

Data augmentation techniques are widely used in low-resource automatic morphological inflection to overcome data sparsity. However, the full implications of these techniques remain poorly understood. In this study, we aim to shed light on…

Automatic speech recognition (ASR) has reached a level of accuracy in recent years, that even outperforms humans in transcribing speech to text. Nevertheless, all current ASR approaches show a certain weakness against ambient noise. To…

Masked speech modeling (MSM) methods such as wav2vec2 or w2v-BERT learn representations over speech frames which are randomly masked within an utterance. While these methods improve performance of Automatic Speech Recognition (ASR) systems,…

Machine learning-based automatic scoring faces challenges with unbalanced student responses across scoring categories. To address this, we introduce a novel text data augmentation framework leveraging GPT-4, a generative large language…

Few-shot prompting and step-by-step reasoning have enhanced the capabilities of Large Language Models (LLMs) in tackling complex tasks including code generation. In this paper, we introduce a prompt selection and augmentation algorithm…