UpStage User Manual

Text2Speech Voices

UpStage’s speech is generated by the Festival Speech Synthesiser, developed at the Centre for Speech Technology Research at Edinburgh University (http://www.cstr.ed.ac.uk/projects/festival/).

An avatar's voice is selected from a dropdown menu when adding a new avatar and changed in the "Manage avatars" section (see section 3.2.3). There are currently about 100 voices on the UpStage server (http://upstage.org.nz:8084); if you are setting up your own UpStage server, please see the technical documentation regarding installing voices.

Voices currently available on UpStage

The voices currently available with UpStage have a filenaming system that describes what kind of voice each one is. Some of the voices speak English in a foreign accent, some speak English in various English accents, and some are designed to speak other languages. The software defaults to a male voice, but we have endeavoured to make female versions of most voices.

You can test the voices on the Avatar Edit screen, by selecting different voices from the drop down menu and entering the text you want to test.

The format is: ["e" or "emb"] _ [native language] - [en] - [modifications]

For example:

e_de – speaks and reads German

e_en – speaks and reads English

e_en-fast-f1 – speaks English quickly, in a female voice

e_en-wm – speaks english in a west midland accent.

Other accents in the e_en series are "n" for north, "sc" for Scots, "rp" for RP, "r" for rhotic (which means it pronounces the r in words like church).

emb_af1 – speaks and reads Afrikaans

emb_af1-en – speaks English in an Afrikaans accent

emb_de4-en-low-slow – speaks english, lowly and slowly, in a german accent

We are in the process of compiling descriptions for all the voices; following is the information so far:

Voice	Male	Female	Accent	Non-Eng	Description
awb_cmu	X		Scottish		Soft, slightly muffled
awb_nitech	X		Scottish		Clear, not very deep
bdl_cmu	X		English?		A little bit quavery
bdl_nitech	X		English?		Firmer than bdl_cmu, a bit higher, but clearer
bud	X		NZ?		Deep, calm
clb_nitech		X	NZ?		Robotic, soft
crunchy					Crunchy - good for witches & effects
default		X	NZ?		Smooth, young
e_en-fast-f1	X		NZ?		fast, boyish
e_en-r-f3	X		NZ?		fast, boyish
e_en-wm-slow	X		Australian??		nasal drawl
e_en-wm-slow-f3	X		Australian??		boyish nasal drawl, computerish & like a learner-reader reading
e_eo	X			foreign
emb_de4	X		German	German	neutral German male
emb_de4-en	X		German		mid-range, clean, English w/German accent
emb_de4-en-low-slow	X		German		pimp's voice: low & lecherous (English w/German accent)
emb_de5	X		German	German	slow low somewhat distorted voice
emb_de5-en	X		German		slow high somewhat distorted voice, English w/German accent
emb_de5-en-high-slow	X		German		mid-high slightly strangulated male, English w/German accent
emb_de7	X		German	German	middle somewhat slow and drawn out male, German
emb_en1-high	X		English		soft mid-range male voice
emb_fr1-en-low	X		European		low & lecherous
emb_fr4-en-high-slow	X		European		mid-high male voice, sounds like he has trouble speaking
emb_hu1-en-slow		X	European?		low soft female voice with slight European accent
emb_nl2	X			Dutch	mid-low male
emb_nl2-en	X		European?		mid-low male voice with slight European accent
emb_pl1		X		Polish?	mid-low calm female
emb_pl1-en		X	Polish?		mid-low calm female with European accent
emb_ro1-en	X
emb_sw1-en-fast	X		Swedish?		mid-low male speaking quickly
emb_sw2-en-high-slow		X	Swedish?		mid-high female with European accent
high	X	X	Computer		boyish computer monotone
rms-faster	X		American
rms-nitech	X		American		Deeper than roger, clear, little bit emphatic
roger	X		English		Thin, proper-sounding, not deep
slow	X		computer		gets slower & lower, very good for effects
slt-cmu		X	American		Flat, slightly muffly
slt-nitech		X	American		Flat, a bit clearer & stronger than slt-cmu

Adding more voices

You can install additional speech plug-ins on your own server to extend the range of voices available to the avatars. As long as you don't mind messing around with the sourcecode a little bit it's not difficult – Patricia Jung explains how she did it (for Linux, using UpStage V1 - note that this is now several years old):

Just add another entry in the VOICES section in Upstage/upstage/voices.py like:

#txt2pho/mbrola:

'de1': ("| /usr/local/mbrola/pipefilt | /usr/local/mbrola/preproc /usr/local/mbrola/Hadifix.abk /usr/local/mbrola/Rules.lst | /usr/local/mbrola/txt2pho -p /usr/local/mbrola/data/ |/usr/local/mbrola/mbrola /usr/local/mbrola/de1/de1 - -",

_fest),

I know, it looks awful but this is only because the command is an awful chain consisting of four commands with a couple of options each and the relevant path:

"| pipefilt ...| preproc ... | txt2pho ... | mbrola ..."

It does some preprocessing (like exchanging all appearances of "z.B." with "zum Beispiel"), then hands the resulting text over to txt2pho and to mbrola.

As long as your command or command chain takes text input from the standard input and outputs the result as sound in raw format on the standard output chain (Unix stuff, ask me if you haven't heard about it) you can put whatever you like in between the "| and the ".

The above mentioned awful command chain will work when one has installed the txt2pho frontend; it uses the de1 female mbrola voice, and you can choose it in the web interface using the name de1.

The only problem with this kind of reconfiguration is: As config.py isn't a nice configuration file but a python script one needs to know at least that python is very picky about vertical alignment: It's extremely important that your new voice entries have the same amount of whitespaces at the beginning of the line as the other voice entries.

The reason it took me so long was TTS: I failed completely and utterly in making the German festival extensions for use with mbrola voices:

http://www.ims.uni-stuttgart.de/phonetik/synthesis/festival_opensource.html

work. Then I tried txt2pho with mbrola:

http://www.ikp.uni-bonn.de/dt/forsch/phonetik/hadifix/HADIFIXforMBROLA.html

(http://bogmog.sourceforge.net/document_show.php3?doc_id=34 has a nice installation description), ignoring festival, and this worked at once.