Perception and Automated Assessment of Audio Quality in User Generated Content

Fazenda B, Kendrick P, Cox T, Li F, Jackson I. Perception and Automated Assessment of Audio Quality in User Generated Content. In: AES Convention 139. Audio Engineering Society; 2015. Paper 9395. Available from: https://aes.org/publications/elibrary-page/?id=17952

@inproceedings{Fazenda2015_17952,
  author = {Fazenda, Bruno and Kendrick, Paul and Cox, Trevor and Li, Francis and Jackson, Iain},
  title = {{Perception and Automated Assessment of Audio Quality in User Generated Content}},
  booktitle = {AES Convention 139},
  note = {Paper 9395},
  year = {2015},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=17952}
}

TY  - CPAPER
TI  - Perception and Automated Assessment of Audio Quality in User Generated Content
AU  - Fazenda, Bruno
AU  - Kendrick, Paul
AU  - Cox, Trevor
AU  - Li, Francis
AU  - Jackson, Iain
T2  - AES Convention 139
M1  - Paper 9395
PY  - 2015
DA  - 2015/10/06
UR  - https://aes.org/publications/elibrary-page/?id=17952
PB  - Audio Engineering Society
LA  - en
AB  - Many of us now carry around technologies that allow us to record sound, whether that is the sound of our child's first music concert on a digital camera or a recording of a practical joke on a mobile phone. However, the production quality of the sound on user-generated content is often very poor: distorted, noisy, with garbled speech or indistinct music. This paper reports the outcomes of a three-year research project on assessment of quality from user generated recordings. Our interest lies in the causes of the poor recording, especially what happens between the sound source and the electronic signal emerging from the microphone. We have investigated typical problems: distortion; wind noise, microphone handling noise, and frequency response. From subjective tests on the perceived quality of such errors and signal features extracted from the audio files we developed perceptual models to automatically predict the perceived quality of audio streams unknown to the model. It is shown that perceived quality is more strongly associated with distortion and frequency response, with wind and handling noise being just slightly less important. The work presented here has applications in areas such as perception and measurement of audio quality, signal processing, and feature detection and machine learning.
ER  -