Diverse Audio Embeddings -- Bringing Features Back Outperforms CLAP!
This work addresses audio classification for researchers and practitioners by showing that integrating domain expertise with end-to-end models can enhance performance, though it is incremental in nature.
The paper tackles audio classification by combining domain-specific handcrafted features (e.g., pitch and timbre) with end-to-end embeddings, resulting in significant performance improvements over purely end-to-end models like CLAP.
With the advent of modern AI architectures, a shift has happened towards end-to-end architectures. This pivot has led to neural architectures being trained without domain-specific biases/knowledge, optimized according to the task. We in this paper, learn audio embeddings via diverse feature representations, in this case, domain-specific. For the case of audio classification over hundreds of categories of sound, we learn robust separate embeddings for diverse audio properties such as pitch, timbre, and neural representation, along with also learning it via an end-to-end architecture. We observe handcrafted embeddings, e.g., pitch and timbre-based, although on their own, are not able to beat a fully end-to-end representation, yet adding these together with end-to-end embedding helps us, significantly improve performance. This work would pave the way to bring some domain expertise with end-to-end models to learn robust, diverse representations, surpassing the performance of just training end-to-end models.