Related papers: A Toolkit for Detecting Spurious Correlations in S…

Audio captioning is a task that generates description of audio based on content. Pre-trained models are widely used in audio captioning due to high complexity. Unless a comprehensive system is re-trained, it is hard to determine how well…

Auditory attention to natural speech is a complex brain process. Its quantification from physiological signals can be valuable to improving and widening the range of applications of current brain-computer-interface systems, however it…

The presence of spurious features interferes with the goal of obtaining robust models that perform well across many groups within the population. A natural remedy is to remove spurious features from the model. However, in this work we show…

We present a comprehensive evaluation of pretrained speech embedding systems for the detection of dysarthric speech using existing accessible data. Dysarthric speech datasets are often small and can suffer from recording biases as well as…

The diagnosis and treatment of individuals with communication disorders offers many opportunities for the application of speech technology, but research so far has not adequately considered: the diversity of conditions, the role of…

Machine learning model bias can arise from dataset composition: correlated sensitive features can distort the downstream classification model's decision boundary and lead to performance differences along these features. Existing de-biasing…

Modern machine learning models are prone to over-reliance on spurious correlations, which can often lead to poor performance on minority groups. In this paper, we identify surprising and nuanced behavior of finetuned models on worst-group…

A large number of works view the automatic assessment of speech from an utterance- or system-level perspective. While such approaches are good in judging overall quality, they cannot adequately explain why a certain score was assigned to an…

Recent advances in using language models to obtain cross-modal audio-text representations have overcome the limitations of conventional training approaches that use predefined labels. This has allowed the community to make progress in tasks…

Social determinants of health (SDOH) extraction from clinical text is critical for downstream healthcare analytics. Although large language models (LLMs) have shown promise, they may rely on superficial cues leading to spurious predictions.…

Label noise is ubiquitous in various machine learning scenarios such as self-labeling with model predictions and erroneous data annotation. Many existing approaches are based on heuristics such as sample losses, which might not be flexible…

In this paper, we address unsupervised domain adaptation under noisy environments, which is more challenging and practical than traditional domain adaptation. In this scenario, the model is prone to overfitting noisy labels, resulting in a…

Large, curated datasets are required to leverage speech-based tools in healthcare. These are costly to produce, resulting in increased interest in data sharing. As speech can potentially identify speakers (i.e., voiceprints), sharing…

In unsupervised domain adaptation, existing theory focuses on situations where the source and target domains are close. In practice, conditional entropy minimization and pseudo-labeling work even when the domain shifts are much larger than…

Selecting application scenarios matching data is important for the automatic speech recognition (ASR) training, but it is difficult to measure the matching degree of the training corpus. This study proposes a unsupervised target-aware data…

English proficiency assessments have become a necessary metric for filtering and selecting prospective candidates for both academia and industry. With the rise in demand for such assessments, it has become increasingly necessary to have the…

Imitation learning field requires expert data to train agents in a task. Most often, this learning approach suffers from the absence of available data, which results in techniques being tested on its dataset. Creating datasets is a…

Learning representations unaffected by superficial characteristics is important to ensure that shifts in these characteristics at test time do not compromise downstream prediction performance. For instance, in healthcare applications, we…

Modern language modeling tasks are often underspecified: for a given token prediction, many words may satisfy the user's intent of producing natural language at inference time, however only one word will minimize the task's loss function at…

Among the most critical limitations of deep learning NLP models are their lack of interpretability, and their reliance on spurious correlations. Prior work proposed various approaches to interpreting the black-box models to unveil the…