EnCodecMAE: Leveraging neural codecs for universal audio representation learning
This work addresses the problem of creating foundational audio models for diverse downstream tasks, representing an incremental improvement over existing self-supervised methods.
The authors tackled universal audio representation learning by proposing EnCodecMAE, which masks audio signals and reconstructs them using discrete units from a neural codec, achieving state-of-the-art performance across speech, music, and environmental sound tasks.
The goal of universal audio representation learning is to obtain foundational models that can be used for a variety of downstream tasks involving speech, music and environmental sounds. To approach this problem, methods inspired by works on self-supervised learning for NLP, like BERT, or computer vision, like masked autoencoders (MAE), are often adapted to the audio domain. In this work, we propose masking representations of the audio signal, and training a MAE to reconstruct the masked segments. The reconstruction is done by predicting the discrete units generated by EnCodec, a neural audio codec, from the unmasked inputs. We evaluate this approach, which we call EnCodecMAE, on a wide range of tasks involving speech, music and environmental sounds. Our best model outperforms various state-of-the-art audio representation models in terms of global performance. Additionally, we evaluate the resulting representations in the challenging task of automatic speech recognition (ASR), obtaining decent results and paving the way for a universal audio representation.