PrincetonComputer SciencePIXL GroupPublications → [Manocha et al. 2022] Local Access
Audio Similarity is Unreliable as a Proxy for Audio Quality

To Appear, Interspeech 2022, September 2022

Pranay Manocha, Zeyu Jin, Adam Finkelstein
Abstract

Many audio processing tasks require perceptual assessment. However, the time and expense of obtaining “gold standard” human judgments limit the availability of such data. Most applications incorporate full reference or other similarity-based metrics (e.g. PESQ) that depend on a clean reference. Researchers have relied on such metrics to evaluate and compare various proposed methods, often concluding that small, measured differences imply one is more effective than another. This paper demonstrates several practical scenarios where similarity metrics fail to agree with human perception, because they: (1) vary with clean references; (2) rely on attributes that humans factor out when considering quality, and (3) are sensitive to imperceptible signal level differences. In those scenarios, we show that no-reference metrics do not suffer from such shortcomings and correlate better with human perception. We conclude therefore that similarity serves as an unreliable proxy for audio quality.
Additional Links
Citation

Pranay Manocha, Zeyu Jin, and Adam Finkelstein.
"Audio Similarity is Unreliable as a Proxy for Audio Quality."
To Appear, Interspeech 2022, September 2022.

BibTeX

@inproceedings{Manocha:2022:ASI,
   author = "Pranay Manocha and Zeyu Jin and Adam Finkelstein",
   title = "Audio Similarity is Unreliable as a Proxy for Audio Quality",
   booktitle = "To Appear, Interspeech 2022",
   year = "2022",
   month = sep
}