Speech Music Discrimination Using an Ensemble of Biased Classifiers

Kim K, Baijal A, Ko BS, Lee S, Hwang I, Kim Y. Speech Music Discrimination Using an Ensemble of Biased Classifiers. In: AES Convention 139. Audio Engineering Society; 2015. Paper 9457. Available from: https://aes.org/publications/elibrary-page/?id=18013

@inproceedings{Kim2015_18013,
  author = {Kim, Kibeom and Baijal, Anant and Ko, Byeong-Seob and Lee, Sangmoon and Hwang, Inwoo and Kim, Youngtae},
  title = {{Speech Music Discrimination Using an Ensemble of Biased Classifiers}},
  booktitle = {AES Convention 139},
  note = {Paper 9457},
  year = {2015},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=18013}
}

TY  - CPAPER
TI  - Speech Music Discrimination Using an Ensemble of Biased Classifiers
AU  - Kim, Kibeom
AU  - Baijal, Anant
AU  - Ko, Byeong-Seob
AU  - Lee, Sangmoon
AU  - Hwang, Inwoo
AU  - Kim, Youngtae
T2  - AES Convention 139
M1  - Paper 9457
PY  - 2015
DA  - 2015/10/06
UR  - https://aes.org/publications/elibrary-page/?id=18013
PB  - Audio Engineering Society
LA  - en
AB  - In this paper we present a novel framework for real-time speech/music discrimination (SMD). The proposed method improves the overall accuracy of automatically classifying the signals into speech, singing, or instrumental categories. In our work, first, we design several groups of classifiers such that each group’s classification decision is biased towards a certain class of sounds; the bias is induced by training different groups of classifiers on perceptual features extracted at different temporal resolutions. Then, we build our system using an ensemble of these biased classifiers organized in a parallel classification fashion. Last, these ensembles are combined with a weighting scheme, which can be tuned in either forward-weighting or inverse-weighting modes, to provide accurate results in real-time. We show, through extensive experimental evaluations, that the proposed ensemble of biased classifiers framework yields superior performance compared to the baseline approach.
ER  -