Related papers: Mitigating Data Imbalance in Automated Speaking As…

Code-switching (CS) refers to the switching of languages within a speech signal and results in language confusion for automatic speech recognition (ASR). To address language confusion, we propose a language alignment loss (LAL) that aligns…

The growing population of L2 English speakers has increased the demand for developing automatic graders for spoken language assessment (SLA). Historically, statistical models, text encoders, and self-supervised speech models have been…

Class imbalance remains a critical challenge in semi-supervised learning (SSL), especially when distributional mismatches between labeled and unlabeled data lead to biased classification. Although existing methods address this issue by…

Self-supervised learning (SSL) approaches such as wav2vec 2.0 and HuBERT models have shown promising results in various downstream tasks in the speech community. In particular, speech representations learned by SSL models have been shown to…

Recent studies have pointed out that many well-developed Visual Question Answering (VQA) models are heavily affected by the language prior problem, which refers to making predictions based on the co-occurrence pattern between textual…

Large language models (LLMs) often demonstrate strong safety performance in high-resource languages, yet exhibit severe vulnerabilities when queried in low-resource languages. We attribute this gap to a mismatch between language-agnostic…

Automatic speech recognition (ASR) outcomes serve as input for downstream tasks, substantially impacting the satisfaction level of end-users. Hence, the diagnosis and enhancement of the vulnerabilities present in the ASR model bear…

Machine learning from training data with a skewed distribution of examples per class can lead to models that favor performance on common classes at the expense of performance on rare ones. AudioSet has a very wide range of priors over its…

Large Language Models (LLMs) have exhibited impressive natural language processing capabilities but often perpetuate social biases inherent in their training data. To address this, we introduce MultiLingual Augmented Bias Testing…

We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context…

Both classification and regression tasks are susceptible to the biased distribution of training data. However, existing approaches are focused on the class-imbalanced learning and cannot be applied to the problems of numerical regression…

Medical image classification is often challenging for two reasons: a lack of labelled examples due to expensive and time-consuming annotation protocols, and imbalanced class labels due to the relative scarcity of disease-positive…

Self-supervised learning (SSL) has transformed speech processing, yet its reliance on massive pre-training datasets remains a bottleneck. While robustness is often attributed to scale and diversity, the role of the data distribution is less…

Detecting fraudulent auto-insurance claims remains a challenging classification problem, largely due to the extreme imbalance between legitimate and fraudulent cases. Standard learning algorithms tend to overfit to the majority class,…

Automatic spoken language assessment systems are becoming more popular in order to handle increasing interests in second language learning. One challenge for these systems is to detect malpractice. Malpractice can take a range of forms,…

In recent years, speech-based self-supervised learning (SSL) has made significant progress in various tasks, including automatic speech recognition (ASR). An ASR model with decent performance can be realized by fine-tuning an SSL model with…

Automatic speech recognition (ASR) systems are known to be sensitive to the sociolinguistic variability of speech data, in which gender plays a crucial role. This can result in disparities in recognition accuracy between male and female…

Detecting out of policy speech (OOPS) content is important but difficult. While machine learning is a powerful tool to tackle this challenging task, it is hard to break the performance ceiling due to factors like quantity and quality…

Fine-tuning large language models (LLMs) with low-rank adaptation (LoRA) is a cost-effective way to incorporate information from a specific dataset. However, when a problem requires incorporating information from multiple datasets - as in…

Bias in AI systems, especially those relying on natural language data, raises ethical and practical concerns. Underrepresentation of certain groups often leads to uneven performance across demographics. Traditional fairness methods, such as…