Binaural Audio Generation via Multi-task Learning

Abstract

We present a learning-based approach for generating binaural audio from mono audio using multi-task learning. Our formulation leverages additional information from two related tasks: the binaural audio generation task and the flipped audio classification task. Our learning model extracts spatialization features from the visual and audio input, predicts the left and right audio channels, and judges whether the left and right channels are flipped. First, we extract visual features using ResNet from the video frames. Next, we perform binaural audio generation and flipped audio classification using separate subnetworks based on visual features. Our learning method optimizes the overall loss based on the weighted sum of the losses of the two tasks. We train and evaluate our model on the FAIR-Play dataset and the YouTube-ASMR dataset. We perform quantitative and qualitative evaluations to demonstrate the benefits of our approach over prior techniques.

References in corpus (10)

• An Overview of Multi-Task Learning in Deep Neural Networks
• Multi-Task Learning for Dense Prediction Tasks: A Survey
• Deep Audio-Visual Speech Recognition
• GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
• Self-Supervised Generation of Spatial Audio for 360 Video
• Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments
• Scene-Aware Audio Rendering via Deep Acoustic Analysis
• Putting a Face to the Voice: Fusing Audio and Visual Signals Across a Video to Determine Speakers
• Sound Synthesis, Propagation, and Rendering: A Survey
• Points2Sound: From mono to binaural audio using 3D point cloud scenes