Real-time Bandwidth Estimation from Offline Expert Demonstrations

no code implementations • 23 Sep 2023 • Aashish Gottipati, Sami Khairy, Gabriel Mittag, Vishak Gopal, Ross Cutler

In this work, we tackle the problem of bandwidth estimation (BWE) for real-time communication systems; however, in contrast to previous works, we leverage the vast efforts of prior heuristic-based BWE methods and synergize these approaches with deep learning-based techniques.

LSTM-based Video Quality Prediction Accounting for Temporal Distortions in Videoconferencing Calls

1 code implementation • 22 Mar 2023 • Gabriel Mittag, Babak Naderi, Vishak Gopal, Ross Cutler

Using these features together with VMAF core features, our proposed model achieves a PCC of 0. 99 on the validation set.

Deep Learning Based Assessment of Synthetic Speech Naturalness

1 code implementation • 23 Apr 2021 • Gabriel Mittag, Sebastian Möller

Further, we show that the reliability of deep learning-based naturalness prediction can be improved by transfer learning from speech quality prediction models that are trained on objective POLQA scores.

Speech Synthesis Transfer Learning +1

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

2 code implementations • 20 Apr 2021 • Gabriel Mittag, Saman Zadtootaghaj, Thilo Michael, Babak Naderi, Sebastian Möller

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.

NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets

1 code implementation • 19 Apr 2021 • Gabriel Mittag, Babak Naderi, Assmaa Chehadi, Sebastian Möller

In this paper, we present an update to the NISQA speech quality prediction model that is focused on distortions that occur in communication networks.