R
Reinhard Sonnleitner
Researcher at Johannes Kepler University of Linz
Publications - 11
Citations - 182
Reinhard Sonnleitner is an academic researcher from Johannes Kepler University of Linz. The author has contributed to research in topics: Voice analysis & Voice activity detection. The author has an hindex of 7, co-authored 11 publications receiving 160 citations.
Papers
More filters
Proceedings ArticleDOI
On the reduction of false positives in singing voice detection
TL;DR: A set of three new audio features designed to reduce the amount of false vocal detections appears to be at least on par with more complex state-of-the-art methods.
Journal ArticleDOI
Robust quad-based audio fingerprinting
TL;DR: An audio fingerprinting method that adapts findings from the field of blind astrometry to define simple, efficiently representable characteristic feature combinations called quads is proposed.
Proceedings Article
Towards Light-Weight, Real-Time-Capable Singing Voice Detection.
TL;DR: It is shown that singing voice detection – the problem of identifying those parts of a polyphonic audio recording where one or several persons sing(s) – can be realised with substantially fewer features than used in current state-of-the-art methods.
Quad-based audio fingerprinting robust to time and frequency scaling
TL;DR: A new audio fingerprinting method is proposed that adapts findings from the field of blind astrometry to define simple, efficiently representable characteristic feature combinations called quads, and accurately estimates the scaling factors of the applied time/frequency distortions.
Book ChapterDOI
From Improved Auto-Taggers to Improved Music Similarity Measures
TL;DR: This paper presents classification experiments that verify the claim that intuitively music similarity measures based on auto-tags should profit from the improvement of the quality of the underlying audio tag predictors and suggests a straight forward way to further improve content-basedMusic similarity measures by improving the underlying auto-taggers.