Skip to main content

Machine Learning for Audio Coding (MLCODEC)

Document Type Approved BOF request
Title Machine Learning for Audio Coding (MLCODEC)
Last updated 2023-06-21
State Approved
Editor Murray Kucherawy
Responsible leadership
Send notices to (None)

Name: Machine Learning for Audio Coding (MLCODEC)


The Opus codec (RFC 6716) was adopted by the IETF in 2012. Since then,
speech and audio processing technology has made significant progress,
thanks in large part to deep learning techniques. It is desirable to
update the existing Opus codec to benefit from recent advances without
breaking compatibility with RFC 6716. Opus has achieved a wide degree of
interoperability by using in-band signaling to avoid negotiation
failure. Implementing new coding technology within Opus would allow
incremental compatible deployment of the updated specification, while
preserving interoperability with the existing billions of Opus-enabled

Formation of this WG was discussed and recommended in the DISPATCH
session at IETF 116. A charter is under review by the IESG. This BoF
request will become a WG session if chartering completes before
IETF 117.

Required Details

  • Status: WG Forming
  • Responsible AD: Murray Kucherawy
  • BOF proponents: Jean-Marc Valin <>
  • BOF chairs: TBD
  • Number of people expected to attend: 50
  • Length of session (1 or 2 hours): 1 hours
  • Conflicts (whole Areas and/or WGs)
  • Chair Conflicts: TBD
  • Technology Overlap: cellar, avtcore
  • Key Participant Conflict: TBD

Information for IAB/IESG

Please see the proposed "mlcodec" charter.


This is expected to be replaced by a regular WG session prior to IETF 117,
at which point a typical WG agenda will be provided.