Multi-Representation Knowledge Distillation For Audio Classification

February 22, 2020 ยท Declared Dead ยท ๐Ÿ› Multimedia tools and applications

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Liang Gao, Kele Xu, Huaimin Wang, Yuxing Peng arXiv ID 2002.09607 Category cs.MM: Multimedia Cross-listed cs.SD, eess.AS Citations 34 Venue Multimedia tools and applications Last Checked 1 month ago
Abstract
As an important component of multimedia analysis tasks, audio classification aims to discriminate between different audio signal types and has received intensive attention due to its wide applications. Generally speaking, the raw signal can be transformed into various representations (such as Short Time Fourier Transform and Mel Frequency Cepstral Coefficients), and information implied in different representations can be complementary. Ensembling the models trained on different representations can greatly boost the classification performance, however, making inference using a large number of models is cumbersome and computationally expensive. In this paper, we propose a novel end-to-end collaborative learning framework for the audio classification task. The framework takes multiple representations as the input to train the models in parallel. The complementary information provided by different representations is shared by knowledge distillation. Consequently, the performance of each model can be significantly promoted without increasing the computational overhead in the inference stage. Extensive experimental results demonstrate that the proposed approach can improve the classification performance and achieve state-of-the-art results on both acoustic scene classification tasks and general audio tagging tasks.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Multimedia

Died the same way โ€” ๐Ÿ‘ป Ghosted