Transformer-based Sequence Labeling for Audio Classification based on MFCCs
This work addresses audio classification for applications like speech and music recognition, presenting an incremental improvement in efficiency.
The paper tackles audio classification by proposing a Transformer-encoder-based model using MFCCs, achieving a highest accuracy of 95.2% on the UrbanSound8k dataset with only 127,544 parameters.
Audio classification is vital in areas such as speech and music recognition. Feature extraction from the audio signal, such as Mel-Spectrograms and MFCCs, is a critical step in audio classification. These features are transformed into spectrograms for classification. Researchers have explored various techniques, including traditional machine and deep learning methods to classify spectrograms, but these can be computationally expensive. To simplify this process, a more straightforward approach inspired by sequence classification in NLP can be used. This paper proposes a Transformer-encoder-based model for audio classification using MFCCs. The model was benchmarked against the ESC-50, Speech Commands v0.02 and UrbanSound8k datasets and has shown strong performance, with the highest accuracy of 95.2% obtained upon training the model on the UrbanSound8k dataset. The model consisted of a mere 127,544 total parameters, making it light-weight yet highly efficient at the audio classification task.