Related papers: Universal Preference-Score-based Pairwise Speech Q…
Current metrics for text-to-image models typically rely on statistical metrics which inadequately represent the real preference of humans. Although recent work attempts to learn these preferences via human annotated images, they reduce the…
Many speech enhancement methods try to learn the relationship between noisy and clean speech, obtained using an acoustic room simulator. We point out several limitations of enhancement methods relying on clean speech targets; the goal of…
Recent advancements in Large Language Models (LLMs) have been remarkable, with new models consistently surpassing their predecessors. These advancements are underpinned by extensive research on various training mechanisms. Among these,…
Open-vocabulary keyword spotting (KWS), which allows users to customize keywords, has attracted increasingly more interest. However, existing methods based on acoustic models and post-processing train the acoustic model with ASR training…
This paper introduces an audio-visual speech enhancement system that leverages score-based generative models, also known as diffusion models, conditioned on visual information. In particular, we exploit audio-visual embeddings obtained from…
Recent progress in generative diffusion models has greatly advanced text-to-video generation. While text-to-video models trained on large-scale, diverse datasets can produce varied outputs, these generations often deviate from user…
Recently, image quality has been generally describedby a mean opinion score (MOS). However, we observe that thequality scores of an image given by a group of subjects are verysubjective and diverse. Thus it is not enough to use a MOS…
Speech quality assessment is a problem for every researcher working on models that produce or process speech. Human subjective ratings, the gold standard in speech quality assessment, are expensive and time-consuming to acquire in a…
In this study, we focus on Singing Voice Mean Opinion Score (SingMOS) prediction. Previous research have shown the performance benefit with the use of state-of-the-art (SOTA) pre-trained models (PTMs). However, they haven't explored speaker…
Session-based recommendation aims to generate recommendations for the next item of users' interest based on a given session. In this manuscript, we develop prospective preference enhanced mixed attentive model (P2MAM) to generate…
In this paper, we present an update to the NISQA speech quality prediction model that is focused on distortions that occur in communication networks. In contrast to the previous version, the model is trained end-to-end and the…
Over the past few decades, computational methods have been developed to estimate perceptual audio quality. These methods, also referred to as objective quality measures, are usually developed and intended for a specific application domain.…
When assessing the causal effect of a binary exposure using observational data, confounder imbalance across exposure arms must be addressed. Matching methods, including propensity score-based matching, can be used to deconfound the causal…
Speech quality assessment (SQA) refers to the evaluation of speech quality, and developing an accurate automatic SQA method that reflects human perception has become increasingly important, in order to keep up with the generative AI boom.…
Supervised masking approaches in the time-frequency domain aim to employ deep neural networks to estimate a multiplicative mask to extract clean speech. This leads to a single estimate for each input without any guarantees or measures of…
Conducting pairwise comparisons is a widely used approach in curating human perceptual preference data. Typically raters are instructed to make their choices according to a specific set of rules that address certain dimensions of image…
Matching users with mutual preferences is a critical aspect of services driven by reciprocal recommendations, such as job search. To produce recommendations in such scenarios, one can predict match probabilities and construct rankings based…
The use of surrogate models instead of computationally expensive simulation codes is very convenient in engineering. Roughly speaking, there are two kinds of surrogate models: the deterministic and the probabilistic ones. These last are…
Direct Preference Optimization (DPO) trains a language model using human preference data, bypassing the explicit reward modeling phase of Reinforcement Learning from Human Feedback (RLHF). By iterating over sentence pairs in a preference…
Recent research on speech enhancement (SE) has seen the emergence of deep-learning-based methods. It is still a challenging task to determine the effective ways to increase the generalizability of SE under diverse test conditions. In this…