• Home
  • History
  • Annotate
Name Date Size #Lines LOC

..03-May-2022-

bin/H26-Aug-2003-2,232989

emu/H07-May-2022-

etc/H15-Sep-2003-2,4302,400

f0/H07-May-2022-

festival/H26-Aug-2003-558,793557,607

festvox/H26-Aug-2003-4,9154,160

lab/H26-Aug-2003-40,54639,414

lpc/H07-May-2022-

mcep/H03-May-2022-

pm/H26-Aug-2003-352,869351,737

pm_lab/H07-May-2022-

wav/H03-May-2022-

.time-stampH A D26-Aug-2003130 98

AREADMEH A D03-Aug-20031.6 KiB5846

COPYINGH A D03-Aug-20032.2 KiB3430

READMEH A D25-Sep-20033 KiB10276

AREADME

1
2CMU ARCTIC BDL
3
4This directory contains a recording of the phonetically balanced US
5English CMU ARCTIC database by BDL, a US English speaker.
6
7See http://www.festvox.org/cmu_arctic/ for details on the
8database coverage and other recordings of this dataset
9
10The format follows the Festvox (http://www.festvox.org) directory
11structure.
12
13The directory structure is
14 bin/
15     basic scripts for building prompts, labelling feature files etc.s
16 cep/
17     Ceptrum files dynamically created in phone autolabellingl
18 dic/
19     Final diphone dictionary final (used at run-time)
20 etc/
21     prompt file, and some labelling templates
22 festival/
23     Not used in diphone bases
24 festvox/
25     scheme voice definition files (used at run-time)
26 group/
27     extracted diphones into signle group file for distribution
28 lab/
29     autolabelled phone labels
30 lar/
31     recorded EGG signal files (not used in this example)
32 lpc/
33     LPC parameters plus residuals, (used at run-time for nongrouped version)
34 mcep/
35     MFCC (Mel Frequency Cepstrum Coefficients) not used in diphone databases
36 pm/
37     Pitchmark files as extract from waveforms (or EGG signal)
38 pm_lab/
39     derived pitchmark labeled files from pm/ enabling emulabel (and others
40     display programs) to show the pitchmarks and waveform files.
41 prompt-cep/
42     cepstrum files for
43 prompt-lab/
44     label files for synthesized prompts
45 prompt-wav/
46     waveforms of synthesized prompts
47 prompt-utts/
48     utterances of synthesized prompts
49 wav/
50     recorded spoken nonsense words (in Microsoft riff (wav) format).
51     If you are using Xwaves you should convert these to NIST format
52
53
54
55
56
57
58

README

1
2CMU ARCTIC BDL 0.95
3
4This directory contains a recording of the phonetically balanced US
5English CMU ARCTIC database by BDL, a US English speaker.
6
7See http://www.festvox.org/cmu_arctic/ for details on the
8database coverage and other recordings of this dataset
9
10The format follows the Festvox (http://www.festvox.org) directory
11structure.
12
13The directory structure is
14 bin/
15     basic scripts for building prompts, labelling feature files etc.s
16 cep/
17     Ceptrum files dynamically created in phone autolabellingl
18 dic/
19     Final diphone dictionary final (used at run-time)
20 etc/
21     prompt file, and some labelling templates
22 festival/
23     Not used in diphone bases
24 festvox/
25     scheme voice definition files (used at run-time)
26 group/
27     extracted diphones into signle group file for distribution
28 lab/
29     autolabelled phone labels
30 lar/
31     recorded EGG signal files (not used in this example)
32 lpc/
33     LPC parameters plus residuals, (used at run-time for nongrouped version)
34 mcep/
35     MFCC (Mel Frequency Cepstrum Coefficients) not used in diphone databases
36 pm/
37     Pitchmark files as extract from waveforms (or EGG signal)
38 pm_lab/
39     derived pitchmark labeled files from pm/ enabling emulabel (and others
40     display programs) to show the pitchmarks and waveform files.
41 prompt-cep/
42     cepstrum files for
43 prompt-lab/
44     label files for synthesized prompts
45 prompt-wav/
46     waveforms of synthesized prompts
47 prompt-utts/
48     utterances of synthesized prompts
49 wav/
50     recorded spoken nonsense words (in Microsoft riff (wav) format).
51     If you are using Xwaves you should convert these to NIST format
52
53INSTALLING AS A FESTIVAL VOICE
54==============================
55
56As distributed this voice may be used as a festival clunits voice with
57versions 1.4.2 and 1.4.3 of Festival (which is available from)
58
59    http://www.cstr.ed.ac.uk/projects/festival/ or
60    http://www.festvox.org/festival/
61
62You can run the voice "in place" or link it into your festival
63installation.
64
65To run "in place" from the database directory
66
67    festival festvox/cmu_us_bdl_arctic_clunits.scm
68    ...
69    festival> (voice_cmu_us_bdl_arctic_clunits)
70    ...
71    festival> (SayText "This is a short introduction ...")
72
73Or to install as voice in your Festival installation it must appear
74as a subdirectory of a subdirectory of a directory listed in the
75Festival variable voice-path.  For standard installations you can
76create the following directory if it doesn't exist
77
78    /...WHATEVER.../festival/lib/voices/us/
79
80For RPM installed systems (such as RedHat) this would be
81
82    /usr/share/festival/voices/us/
83
84In that directory create a symbolic link to the arctic voice as in
85
86    ln -s /usr/local/arctic/cmu_us_bdl_arctic cmu_us_bdl_arctic_clunits
87
88Note the name in the us/ directory must be the name of the voice.
89
90This should allow festival to find the voice automatically thus
91
92    festival
93    ...
94    festival> (voice_cmu_us_bdl_arctic_clunits)
95    ...
96    festival> (SayText "This is a short introduction ...")
97
98
99
100
101
102