Complexity Scalable Perceptual Tempo Estimation from HE-AAC Encoded Music

Hollosi D, Biswas A. Complexity Scalable Perceptual Tempo Estimation from HE-AAC Encoded Music. In: AES Convention 128. Audio Engineering Society; 2010. Paper 8109. Available from: https://aes.org/publications/elibrary-page/?id=15406

@inproceedings{Hollosi2010_15406,
  author = {Hollosi, Danilo and Biswas, Arijit},
  title = {{Complexity Scalable Perceptual Tempo Estimation from HE-AAC Encoded Music}},
  booktitle = {AES Convention 128},
  note = {Paper 8109},
  year = {2010},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=15406}
}

TY  - CPAPER
TI  - Complexity Scalable Perceptual Tempo Estimation from HE-AAC Encoded Music
AU  - Hollosi, Danilo
AU  - Biswas, Arijit
T2  - AES Convention 128
M1  - Paper 8109
PY  - 2010
DA  - 2010/05/06
UR  - https://aes.org/publications/elibrary-page/?id=15406
PB  - Audio Engineering Society
LA  - en
AB  - A modulation frequency-based method for perceptual tempo estimation from HE-AAC encoded music is proposed. The method is designed to work on the fully-decoded PCM-domain; the intermediate HE-AAC transform-domain after partial decoding; and directly on the HE-AAC compressed-domain using Spectral Band Replication (SBR) payload. This offers complexity scalable solutions. We demonstrate that SBR payload is an ideal proxy for tempo estimation directly from HE-AAC bit-streams without even decoding them. A perceptual tempo correction stage is proposed based on rhythmic features to correct for octave errors in every domain. Experimental results show that the proposed method significantly outperforms two commercially available systems, both in terms of accuracy and computational speed.
ER  -