Evaluating off-the-shelf machine listening and natural language models for automated audio captioning

Weck, Benno; Favory, Xavier; Drossos, Konstantinos; Serra, Xavier

Evaluating off-the-shelf machine listening and natural language models for automated audio captioning

License

Citation

Weck B, Favory X, Drossos K, Serra X. Evaluating off-the-shelf machine listening and natural language models for automated audio captioning. In: Font F, Mesaros A, Ellis DPW, Fonseca E, Fuentes M, Elizalde B, editors. Proceedings of the 6th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2021); 2021 Nov 15-19; Online. Barcelona: Universitat Pompeu Fabra, Music Technology Group; 2021. p. 60-4.

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.