On Training Targets and Objective Functions for Deep-learning-based Audio-visual Speech Enhancement
Year: 2019
Type: conference-paper
Abstract: Audio-visual speech enhancement (AV-SE) is the task of improving speech quality and intelligibility in a noisy environment using audio and visual information from a talker. Recently, deep learning techniques have been adopted to solve the AV-SE task in a supervised manner. In this context, the choice of the target, i.e. the quantity to be estimated, and the objective function, which quantifies the quality of this estimate, to be used for training is critical for the performance. This work is the first that presents an experimental study of a range of different targets and objective functions used to train a deep-learning-based AV-SE system. The results show that the approaches that directly estimate a mask perform the best overall in terms of estimated speech quality and intelligibility, although the model that directly estimates the log magnitude spectrum performs as good in terms of estimated speech quality.
Institutions: Aalborg University, Oticon (Denmark)
Language: English
Topic: Speech and Audio Processing
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2901702433