Music Thumbnailing for Radio Podcasts: A Listener Evaluation

Mehrabi A, Harte C, Baume C, Dixon S. Music Thumbnailing for Radio Podcasts: A Listener Evaluation. J Audio Eng Soc. 2017;65(6):474-481. doi:10.17743/jaes.2017.0011

@article{Mehrabi2017_18780,
  author = {Mehrabi, Adib and Harte, Chris and Baume, Chris and Dixon, Simon},
  title = {{Music Thumbnailing for Radio Podcasts: A Listener Evaluation}},
  journal = {Journal of the Audio Engineering Society},
  volume = {65},
  number = {6},
  pages = {474--481},
  year = {2017},
  month = jun,
  publisher = {Audio Engineering Society},
  doi = {10.17743/jaes.2017.0011},
  url = {https://doi.org/10.17743/jaes.2017.0011}
}

TY  - JOUR
TI  - Music Thumbnailing for Radio Podcasts: A Listener Evaluation
AU  - Mehrabi, Adib
AU  - Harte, Chris
AU  - Baume, Chris
AU  - Dixon, Simon
T2  - Journal of the Audio Engineering Society
J2  - J. Audio Eng. Soc.
VL  - 65
IS  - 6
SP  - 474
EP  - 481
PY  - 2017
DA  - 2017/06/06
DO  - 10.17743/jaes.2017.0011
UR  - https://doi.org/10.17743/jaes.2017.0011
PB  - Audio Engineering Society
LA  - en
AB  - When radio podcasts are produced from previously broadcast material, thumbnails of songs that were featured in the original program are often included. Such thumbnails provide a summary of the music content. Because creating thumbnails is a labor-intensive process, this is an ideal application for automatic music editing, but it raises the question of how a piece of music can be best summarized. Researchers asked 120 listeners to rate the quality of thumbnails generated by eight methods (five automatic and three manual). The listeners were asked to rate the editing methods based on the song part selection and transition quality in the edited clips, as well as the perceived overall quality. The listener ratings showed a preference for editing methods where the edit points were quantized to bar positions, but there was no preference for whether the chorus was included or not. Ratings for two automatic editing methods were not significantly different from their manual counterparts. This suggests that automatic editing methods can be used to create production-quality thumbnails.
ER  -