[vorbis-dev] patents and separate entropy coding

Gregory Maxwell greg at linuxpower.cx
Sat Dec 16 19:21:32 PST 2000

On Fri, Dec 15, 2000 at 08:39:20PM +0100, Lourens Veen wrote:
> Roger, sorry 'bout that. I am talking about patent claim #US5579430
> which is entitled Digital encoding process and can be found at
> http://www.delphion.com/details?pn=US05579430__
> It patents "A digital encoding process for transmitting and/or storing
> acoustical sigs and, in particular, music signals, in which scanned
> values of the acoustical signal are transformed by means of a
> transformation or a filter bank into a sequence of second scanned
> values, which reproduce the spectral composition of the acoustical
> signal, and the sequence of second scanned values is quantized in
> accordance with the requirements with varying precision and is partially
> or entirely encoded by an optimum encoder, and in which a corresponding
> decoding and inverse transformation takes place during the
> reproduction."
> I'd say that that is what Vorbis does, although I haven't looked at the
> algorithm very closely.

No GUI browser right now so I can't read the actual claims, but I would
suspect that the patent is actually more specific then that, as something
the broad would never hold up in court.

Furthermore, Vorbis does not perform as the above describes. Vorbis
subtracts a smooth spectral power curve from the mdct data and then chops
the residue into codewords. Quantization is never directly performed on the
mdct lines.

--- >8 ----
List archives:  http://www.xiph.org/archives/
Ogg project homepage: http://www.xiph.org/ogg/
To unsubscribe from this list, send a message to 'vorbis-dev-request at xiph.org'
containing only the word 'unsubscribe' in the body.  No subject is needed.
Unsubscribe messages sent to the list will be ignored/filtered.

More information about the Vorbis-dev mailing list