Related papers: A Data-driven Cognitive Salience Model for Objecti…
Speech quality assessment has been a critical component in many voice communication related applications such as telephony and online conferencing. Traditional intrusive speech quality assessment requires the clean reference of the degraded…
Incorporating the audio stream enables Video Saliency Prediction (VSP) to imitate the selective attention mechanism of human brain. By focusing on the benefits of joint auditory and visual information, most VSP methods are capable of…
One of the challenges in computational acoustics is the identification of models that can simulate and predict the physical behavior of a system generating an acoustic signal. Whenever such models are used for commercial applications an…
Due to the over-emphasize of the quantity of data, the data quality has often been overlooked. However, not all training data points contribute equally to learning. In particular, if mislabeled, it might actively damage the performance of…
Generative speech enhancement has recently shown promising advancements in improving speech quality in noisy environments. Multiple diffusion-based frameworks exist, each employing distinct training objectives and learning techniques. This…
MOS (Mean Opinion Score) is a subjective method used for the evaluation of a system's quality. Telecommunications (for voice and video), and speech synthesis systems (for generated speech) are a few of the many applications of the method.…
Modern computer vision foundation models are trained on massive amounts of data, incurring large economic and environmental costs. Recent research has suggested that improving data quality can significantly reduce the need for data…
Gradient-based saliency methods are widely used to interpret deep neural networks, yet they often produce noisy and unstable explanations that poorly align with semantically meaningful input features. We argue that a fundamental cause of…
Data-driven models based on deep learning algorithms intend to overcome the limitations of traditional constitutive modelling by directly learning from data. However, the need for extensive data that collate the full state of the material…
Synthesizing natural head motion to accompany speech for an embodied conversational agent is necessary for providing a rich interactive experience. Most prior works assess the quality of generated head motion by comparing them against a…
In educational technology and learning sciences, there are multiple uses for a predictive model of whether a student will perform a task correctly or not. For example, an intelligent tutoring system may use such a model to estimate whether…
Modelling of early language acquisition aims to understand how infants bootstrap their language skills. The modelling encompasses properties of the input data used for training the models, the cognitive hypotheses and their algorithmic…
In an earlier study, we gathered perceptual evaluations of the audio, video, and audiovisual quality for 360 audiovisual content. This paper investigates perceived audiovisual quality prediction based on objective quality metrics and…
The paper presents a data-driven predictive control framework based on an implicit input-output mapping derived directly from the signal matrix of collected data. This signal matrix model is derived by maximum likelihood estimation with…
Audio-visual saliency prediction can draw support from diverse modality complements, but further performance enhancement is still challenged by customized architectures as well as task-specific loss functions. In recent studies, denoising…
Most existing CNN-based salient object detection methods can identify local segmentation details like hair and animal fur, but often misinterpret the real saliency due to the lack of global contextual information caused by the…
Any prediction from a model is made by a combination of learning history and test stimuli. This provides significant insights for improving model interpretability: {\it because of which part(s) of which training example(s), the model…
Effective optimization is essential for interactive systems to provide a satisfactory user experience. However, it is often challenging to find an objective to optimize for. Generally, such objectives are manually crafted and rarely capture…
There is growing interest in incorporating eye-tracking data and other implicit measures of human language processing into natural language processing (NLP) pipelines. The data from human language processing contain unique insight into…
The idea of automatizing the assessment of objectoriented design is not new. Different approaches define and apply their own quality models, which are composed of single metrics or combinations thereof, to operationalize software design.…