English
Related papers

Related papers: Universal Preference-Score-based Pairwise Speech Q…

200 papers

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…

Computer Vision and Pattern Recognition · Computer Science 2024-05-24 Sixian Zhang , Bohan Wang , Junqiang Wu , Yan Li , Tingting Gao , Di Zhang , Zhongyuan Wang

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…

Computation and Language · Computer Science 2018-12-26 Geonmin Kim , Hwaran Lee , Bo-Kyeong Kim , Sang-Hoon Oh , Soo-Young Lee

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,…

Computation and Language · Computer Science 2024-12-12 Hansle Gwon , Imjin Ahn , Young-Hak Kim , Sanghyun Park , Tae Joon Jun

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…

Audio and Speech Processing · Electrical Eng. & Systems 2023-12-18 Ao Zhang , Pan Zhou , Kaixun Huang , Yong Zou , Ming Liu , Lei Xie

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…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-05 Julius Richter , Simone Frintrop , Timo Gerkmann

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…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Runtao Liu , Haoyu Wu , Zheng Ziqiang , Chen Wei , Yingqing He , Renjie Pi , Qifeng Chen

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…

Image and Video Processing · Electrical Eng. & Systems 2022-03-03 Yixuan Gao , Xiongkuo Min , Wenhan Zhu , Xiao-Ping Zhang , Guangtao Zhai

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…

Sound · Computer Science 2023-05-25 Lorenz Diener , Marju Purin , Sten Sootla , Ando Saabas , Robert Aichner , Ross Cutler

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…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-04 Orchid Chetia Phukan , Girish , Mohd Mujtaba Akhtar , Swarup Ranjan Behera , Pailla Balakrishna Reddy , Arun Balaji Buduru , Rajesh Sharma

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…

Information Retrieval · Computer Science 2024-07-11 Bo Peng , Chang-Yu Tai , Srinivasan Parthasarathy , Xia Ning

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…

Audio and Speech Processing · Electrical Eng. & Systems 2021-12-15 Gabriel Mittag , Babak Naderi , Assmaa Chehadi , Sebastian Möller

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.…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-25 Matteo Torcoli , Thorsten Kastner , Jürgen Herre

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…

Methodology · Statistics 2024-10-01 Ernesto Ulloa-Pérez , Marco Carone , Alex Luedtke

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.…

Sound · Computer Science 2025-08-29 Wen-Chin Huang

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…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-16 Huajian Fang , Dennis Becker , Stefan Wermter , Timo Gerkmann

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…

Computer Vision and Pattern Recognition · Computer Science 2020-11-24 Hossein Talebi , Ehsan Amid , Peyman Milanfar , Manfred K. Warmuth

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…

Information Retrieval · Computer Science 2024-09-19 Shuhei Goda , Yudai Hayashi , Yuta Saito

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…

Applications · Statistics 2015-12-24 Malek Ben Salem , Olivier Roustant , Fabrice Gamboa , Lionel Tomaso

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…

Machine Learning · Computer Science 2024-10-31 Jae Hyeon Cho , Minkyung Park , Byung-Jun Lee

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…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-01 Ryandhimas E. Zezario , Chiou-Shann Fuh , Hsin-Min Wang , Yu Tsao