Continued improvments section
This commit is contained in:
+11
-6
@@ -338,21 +338,26 @@
|
||||
usefulness. Some initial ideas for improvments are detailed in this
|
||||
section. These range from reasonably simple modifications that could not be
|
||||
implemented purely due to time constraints, to more complex ideas that may
|
||||
take a considerable amount of work.
|
||||
take a considerable amount of work.\\
|
||||
|
||||
The current implementation uses only a small and relatively basic subset of
|
||||
the audio descriptors available. This limits the analysis of audio and thus
|
||||
the quality of matches. Using a larger set of more advanced descriptors may
|
||||
improve quality from this perspective. One way would be to incorporate the
|
||||
open source Essentia audio descriptors *citation needed* giving the project
|
||||
access to a vast quantity of descriptors for analysis.
|
||||
open source Essentia audio descriptors~\parencite{Essentia2016} giving the
|
||||
project access to a vast quantity of descriptors for analysis.\\
|
||||
|
||||
Better ways of windowing using SOLA/PSOLA methods
|
||||
|
||||
High quantity of parameters is very time consuming ~\parencite{Petrushin2007}
|
||||
Replacing the hanning window function used for grain windowing with a short
|
||||
cross fade at grain overlaps should reduce amplitude modulation, resulting
|
||||
in smoother transitions between grains. This might be further improved
|
||||
through calculating the point of maximum similarity by cross-correlating
|
||||
overlapping sections, as described by~\textcite[p.191-193]{Zolzer2011} in
|
||||
the SOLA algorithm.\\
|
||||
|
||||
Replacment of HDF5 to allow parallel processing
|
||||
possible use of more sophisticated database management system as demonstarted in the Catapillar project.
|
||||
|
||||
High quantity of parameters is very time consuming ~\parencite{Petrushin2007}
|
||||
|
||||
Spectral matching~\parencite{Hoffman2009}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user