Singing Voice Detection across Different Music Genres

Scholz F, Vatolkin I, Rudolph G. Singing Voice Detection across Different Music Genres. In: AES Conference: 2017 AES International Conference on Semantic Audio. Audio Engineering Society; 2017.pp. P2-1:1-8. Available from: https://aes.org/publications/elibrary-page/?id=18771

@inproceedings{Scholz2017_18771,
  author = {Scholz, Florian and Vatolkin, Igor and Rudolph, Günter},
  title = {{Singing Voice Detection across Different Music Genres}},
  booktitle = {AES Conference: 2017 AES International Conference on Semantic Audio},
  pages = {P2-1:1-8},
  year = {2017},
  month = jun,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=18771}
}

TY  - CPAPER
TI  - Singing Voice Detection across Different Music Genres
AU  - Scholz, Florian
AU  - Vatolkin, Igor
AU  - Rudolph, Günter
T2  - AES Conference: 2017 AES International Conference on Semantic Audio
SP  - 1
EP  - 8
M1  - Paper P2-1
PY  - 2017
DA  - 2017/06/06
UR  - https://aes.org/publications/elibrary-page/?id=18771
PB  - Audio Engineering Society
LA  - en
AB  - Most of recent studies on vocal detection in audio recordings typically focus either on the development of new features or on classification methods. The impact of training and test data is largely neglected, leading to weaknesses in the design of databases which do not cover differences of vocal techniques across music genres. In this paper, we compare approaches for singing voice detection on individual genres. For both methods with the best performance, we further investigate the impact of disjunct distribution of training and test tracks with regard to their genres. In particular, the tracks of electronic genres, which are barely contained in public databases for vocal recognition, contribute to a better classification performance identifying vocals in tracks of other genres.
ER  -