Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning
arXiv:2110.07410
Abstract
Automated audio captioning (AAC) is the task of automatically generating textual descriptions for general audio signals. A captioning system has to identify various information from the input signal and express it with natural language. Existing works mainly focus on investigating new methods and try to improve their performance measured on existing datasets. Having attracted attention only recently, very few works on AAC study the performance of existing pre-trained audio and natural language processing resources. In this paper, we evaluate the performance of off-the-shelf models with a Transformer-based captioning approach. We utilize the freely available Clotho dataset to compare four different pre-trained machine listening models, four word embedding models, and their combinations in many different settings. Our evaluation suggests that YAMNet combined with BERT embeddings produces the best captions. Moreover, in general, fine-tuning pre-trained word embeddings can lead to better performance. Finally, we show that sequences of audio embeddings can be processed using a Transformer encoder to produce higher-quality captions.
arXiv comment5 pages, 4 figures. Accepted at Detection and Classification of Acoustic Scenes and Events 2021 (DCASE2021)
References in corpus (11)
- Distributed Representations of Words and Phrases and their Compositionality
- Sequence to Sequence Learning with Neural Networks
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- YouTube-8M: A Large-Scale Video Classification Benchmark
- Improved Image Captioning via Policy Gradient optimization of SPIDEr
- Audio Caption: Listen and Tell
- Audio Captioning using Pre-Trained Large-Scale Language Model Guided by Audio-based Similar Caption Retrieval
- Multi-task Regularization Based on Infrequent Classes for Audio Captioning
- Audio Captioning using Gated Recurrent Units
- COALA: Co-Aligned Autoencoders for Learning Semantically Enriched Audio Representations
- Temporal Sub-sampling of Audio Feature Sequences for Automated Audio Captioning