Ticket #468 (new defect)

Opened 11 years ago

Last modified 11 years ago

VoxForge pron dict not using CMU 0.6; using xVoice unstressed dict...

Reported by: kmaclean Owned by: kmaclean
Priority: major Milestone: Acoustic Model 0.1.2
Component: Acoustic Model Version: Acoustic Model 0.1.1
Keywords: Cc:

Description (last modified by kmaclean) (diff)

from this post:

For Festival CMU generated phonemes I do not find documentation for DX and IX. Are these needed for efficient phonetic alignment?

Now that is an interesting question...

I have not looked at this in a while, but it seems that when I first created the VoxForge? dictionary, I could not use CMU dict v0.6 (contrary to what I state in this FAQ entry: What is the VoxForge? phoneset?) but actually used the CMU unstressed dictionary from the xvoice site (see Notes file).

All this time, I have assumed that CMU dict v0.6 and the CMU unstressed dictionary used the same phone set, but that does not seem to be the case, e.g.:

xvoice cmu-unstressed:

ABBREVIATED AX B R IY V IY EY DX AX D

Voxforge pronunciation dictionary

ABBREVIATED [ABBREVIATED] ax b r iy v iy ey dx ax d

cmu dict v0.6 (stressed - remove numbers for unstressed)

ABBREVIATED AH0 B R IY1 V IY0 EY2 T AH0 D

Speech Recognition engines don't really care what identifier you use for a particular phoneme, as long as you are consistent. The CMU pronunciation dictionary is the de facto standard open source pronunciation dictionary (for English), so I would recommend that you use the most current version (CMU dict v0.7).

Change History

comment:1 Changed 11 years ago by kmaclean

  • Description modified (diff)
  • Summary changed from VoxForge pron dict not using CMU 0.6 using xVoice unstressed dict... to VoxForge pron dict not using CMU 0.6; using xVoice unstressed dict...
Note: See TracTickets for help on using tickets.