Generative Modeling of Metadata for Machine Learning Based Audio Content Classification

Bharitkar SG. Generative Modeling of Metadata for Machine Learning Based Audio Content Classification. In: AES Convention 147. Audio Engineering Society; 2019. Paper 564. Available from: https://aes.org/publications/elibrary-page/?id=20587

@inproceedings{Bharitkar2019_20587,
  author = {Bharitkar, Sunil G.},
  title = {{Generative Modeling of Metadata for Machine Learning Based Audio Content Classification}},
  booktitle = {AES Convention 147},
  note = {Paper 564},
  year = {2019},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=20587}
}

TY  - CPAPER
TI  - Generative Modeling of Metadata for Machine Learning Based Audio Content Classification
AU  - Bharitkar, Sunil G.
T2  - AES Convention 147
M1  - Paper 564
PY  - 2019
DA  - 2019/10/06
UR  - https://aes.org/publications/elibrary-page/?id=20587
PB  - Audio Engineering Society
LA  - en
AB  - Automatic content classification technique is an essential tool in multimedia applications. Present research for audio-based classifiers look at short- and long-term analysis of signals, using both temporal and spectral features. In this paper we present a neural network to classify between the movie (cinematic, TV shows), music, and voice using metadata contained in either the audio/video stream. Towards this end, statistical models of the various metadata are created since a large metadata dataset is not available. Subsequently, synthetic metadata are generated from these statistical models, and the synthetic metadata is input to the ML classifier as feature vectors. The resulting classifier is then able to classify real-world content (e.g., YouTube) with an accuracy ˜ 90% with very low latency (viz., ˜ on an average 7 ms) based on real-world metadata.
ER  -