Audiovisual Transformer Architectures for Large-Scale Classification and Synchronization of Weakly Labeled Audio Events

Abstract

We tackle the task of environmental event classification by drawing inspiration from the transformer neural network architecture used in machine translation. We modify this attention-based feedforward structure in such a way that allows the resulting model to use audio as well as video to compute sound event predictions. We perform extensive experiments with these adapted transformers on an audiovisual data set, obtained by appending relevant visual information to an existing large-scale weakly labeled audio collection. The employed multi-label data contains clip-level annotation indicating the presence or absence of 17 classes of environmental sounds, and does not include temporal information. We show that the proposed modified transformers strongly improve upon previously introduced models and in fact achieve state-of-the-art results. We also make a compelling case for devoting more attention to research in multimodal audiovisual classification by proving the usefulness of visual information for the task at hand,namely audio event recognition. In addition, we visualize internal attention patterns of the audiovisual transformers and in doing so demonstrate their potential for performing multimodal synchronization.

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• TensorFlow: A system for large-scale machine learning
• Convolutional Sequence to Sequence Learning
• YouTube-8M: A Large-Scale Video Classification Benchmark
• Sound source detection, localization and classification using consecutive ensemble of CRNN models
• Surrey-cvssp system for DCASE2017 challenge task4
• Weakly Supervised Representation Learning for Unsynchronized Audio-Visual Events

Cited by in corpus (5)

• Parameter Efficient Multimodal Transformers for Video Representation Learning
• A Transformer-based Audio Captioning Model with Keyword Estimation
• Multi-encoder attention-based architectures for sound recognition with partial visual assistance
• TriBERT: Full-body Human-centric Audio-visual Representation Learning for Visual Sound Separation
• Audiovisual transfer learning for audio tagging and sound event detection