Towards speeding audio eq interface building with transfer learning

Bryan Pardo, David Little, Darren Gergle

Research output: Contribution to journalConference articlepeer-review

4 Scopus citations


Potential users of audio production software, such as parametric audio equalizers, may be discouraged by the complexity of the interface. A new approach creates a personalized on-screen slider that lets the user manipulate the audio in terms of a descriptive term (e.g. “warm”), without the user needing to learn or use the interface of an equalizer. This system learns mappings by presenting a sequence of sounds to the user and correlating the gain in each frequency band with the user’s preference rating. The system speeds learning through transfer learning. Results on a study of 35 participants show how an effective, personalized audio manipulation tool can be automatically built after only three ratings from the user.

Original languageEnglish (US)
JournalProceedings of the International Conference on New Interfaces for Musical Expression
StatePublished - 2012
Event12th International conference on New Interfaces for Musical Expression, NIME 2012 - Ann Arbor, United States
Duration: May 21 2012May 23 2012


  • Human computer interaction
  • Multimedia production
  • Music
  • Transfer learning

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Signal Processing
  • Instrumentation
  • Music
  • Human-Computer Interaction
  • Hardware and Architecture
  • Computer Science Applications


Dive into the research topics of 'Towards speeding audio eq interface building with transfer learning'. Together they form a unique fingerprint.

Cite this