Log In Sign Up

Bias-Aware Loss for Training Image and Speech Quality Prediction Models from Multiple Datasets

by   Gabriel Mittag, et al.

The ground truth used for training image, video, or speech quality prediction models is based on the Mean Opinion Scores (MOS) obtained from subjective experiments. Usually, it is necessary to conduct multiple experiments, mostly with different test participants, to obtain enough data to train quality models based on machine learning. Each of these experiments is subject to an experiment-specific bias, where the rating of the same file may be substantially different in two experiments (e.g. depending on the overall quality distribution). These different ratings for the same distortion levels confuse neural networks during training and lead to lower performance. To overcome this problem, we propose a bias-aware loss function that estimates each dataset's biases during training with a linear function and considers it while optimising the network weights. We prove the efficiency of the proposed method by training and validating quality prediction models on synthetic and subjective image and speech quality datasets.


page 1

page 2

page 3

page 4


MBNet: MOS Prediction for Synthesized Speech with Mean-Bias Network

Mean opinion score (MOS) is a popular subjective metric to assess the qu...

LDNet: Unified Listener Dependent Modeling in MOS Prediction for Synthetic Speech

An effective approach to automatically predict the subjective rating for...

Perceptually Guided End-to-End Text-to-Speech

Several fast text-to-speech (TTS) models have been proposed for real-tim...

Curiously Effective Features for Image Quality Prediction

The performance of visual quality prediction models is commonly assumed ...

DNN No-Reference PSTN Speech Quality Prediction

Classic public switched telephone networks (PSTN) are often a black box ...

Can Strategic Data Collection Improve the Performance of Poverty Prediction Models?

Machine learning-based estimates of poverty and wealth are increasingly ...

A Simple Model for Subject Behavior in Subjective Experiments

In a subjective experiment to evaluate the perceptual audiovisual qualit...

Code Repositories


Bias-Aware Loss for Training Image and Speech Quality Prediction Models from Multiple Dataset

view repo