An Investigation of Temporal Feature Integration for a Low-Latency Classification with Application to Speech/Music/Mix Classification

Flocon-Cholet J, Faure J, Guérin A, Scalart P. An Investigation of Temporal Feature Integration for a Low-Latency Classification with Application to Speech/Music/Mix Classification. In: AES Convention 137. Audio Engineering Society; 2014. Paper 9180. Available from: https://aes.org/publications/elibrary-page/?id=17503

@inproceedings{FloconCholet2014_17503,
  author = {Flocon-Cholet, Joachim and Faure, Julien and Guérin, Alexandre and Scalart, Pascal},
  title = {{An Investigation of Temporal Feature Integration for a Low-Latency Classification with Application to Speech/Music/Mix Classification}},
  booktitle = {AES Convention 137},
  note = {Paper 9180},
  year = {2014},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=17503}
}

TY  - CPAPER
TI  - An Investigation of Temporal Feature Integration for a Low-Latency Classification with Application to Speech/Music/Mix Classification
AU  - Flocon-Cholet, Joachim
AU  - Faure, Julien
AU  - Guérin, Alexandre
AU  - Scalart, Pascal
T2  - AES Convention 137
M1  - Paper 9180
PY  - 2014
DA  - 2014/10/06
UR  - https://aes.org/publications/elibrary-page/?id=17503
PB  - Audio Engineering Society
LA  - en
AB  - In this paper we propose several methodologies for the use of feature integration and evaluate them in a low-latency classification framework. These general methodologies are based on three key aspects that will be assessed in this study: the selection of the features that have to be temporally integrated, the choice of the integration techniques, i.e., how the temporal information is extracted, and the size of the integration window. The experiments carried out for the speech/music/mix classification task show that the different methodologies have a significant impact on the global performance. Compared to the state of the art procedures, the methodologies we proposed achieved the best performance, even with the low-latency constraints.
ER  -