1D/2D Deep CNNs vs. Temporal Feature Integration for General Audio Classification

Vrysis L, Tsipas N, Thoidis I, Dimoulas C. 1D/2D Deep CNNs vs. Temporal Feature Integration for General Audio Classification. J Audio Eng Soc. 2020;68(1/2):66-77. doi:10.17743/jaes.2019.0058

@article{Vrysis2020_20722,
  author = {Vrysis, Lazaros and Tsipas, Nikolaos and Thoidis, Iordanis and Dimoulas, Charalampos},
  title = {{1D/2D Deep CNNs vs. Temporal Feature Integration for General Audio Classification}},
  journal = {Journal of the Audio Engineering Society},
  volume = {68},
  number = {1/2},
  pages = {66--77},
  year = {2020},
  month = jan,
  publisher = {Audio Engineering Society},
  doi = {10.17743/jaes.2019.0058},
  url = {https://doi.org/10.17743/jaes.2019.0058}
}

TY  - JOUR
TI  - 1D/2D Deep CNNs vs. Temporal Feature Integration for General Audio Classification
AU  - Vrysis, Lazaros
AU  - Tsipas, Nikolaos
AU  - Thoidis, Iordanis
AU  - Dimoulas, Charalampos
T2  - Journal of the Audio Engineering Society
J2  - J. Audio Eng. Soc.
VL  - 68
IS  - 1/2
SP  - 66
EP  - 77
PY  - 2020
DA  - 2020/01/06
DO  - 10.17743/jaes.2019.0058
UR  - https://doi.org/10.17743/jaes.2019.0058
PB  - Audio Engineering Society
LA  - en
AB  - Semantic audio analysis has become a fundamental task in modern audio applications, making the improvement and optimization of classification algorithms a necessity. Standard frame-based audio classification methods have been optimized, and modern approaches introduce engineering methodologies that capture the temporal dependency between successive feature observations, following the process of temporal feature integration. Moreover, the deployment of the convolutional neural networks defined a new era on semantic audio analysis. This paper attempts a thorough comparison between standard feature-based classification strategies, state-of-the-art temporal feature integration tactics, and 1D/2D deep convolutional neural network setups on typical audio classification tasks. Experiments focus on optimizing a lightweight configuration for convolutional network topologies on a Speech/Music/Other classification scheme that can be deployed on various audio information retrieval tasks, such as voice activity detection, speaker diarization, or speech emotion recognition. The main target of this work is the establishment of an optimized protocol for constructing deep convolutional topologies on general audio detection classification schemes, minimizing complexity and computational needs.
ER  -