ARPABET (also spelled ARPAbet) is a set of phonetic transcription codes developed by Advanced Research Projects Agency (ARPA) as a part of their Speech Understanding Research project in the 1970s. It represents phonemes and allophones of General American English with distinct sequences of ASCII characters. Two systems, one representing each segment with one character (alternating upper- and lower-case letters) and the other with one or two (case-insensitive), were devised, the latter being far more widely adopted.[1]

ARPABET has been used in several speech synthesizers, including Computalker for the S-100 system, SAM for the Commodore 64, SAY for the Amiga, TextAssist for the PC and Speakeasy from Intelligent Artefacts which used the Votrax SC-01 speech synthesiser IC. It is also used in the CMU Pronouncing Dictionary. A revised version of ARPABET is used in the TIMIT corpus.[1]

Symbols

edit

Stress is indicated by a digit immediately following a vowel. Auxiliary symbols are identical in 1- and 2-letter codes. In 2-letter notation, segments are separated by a space.

Vowels[2]
ARPABET IPA Example(s)
1-letter 2-letter
a AA ɑ~ɒ balm, bot (with father–bother merger)
@ AE æ bat
A AH ʌ butt
c AO ɔ caught, story
W AW bout
x AX ə comma
AXR[3] ɚ letter, forward
Y AY bite
E EH ɛ bet
R ER ɝ bird, foreword
e EY bait
I IH ɪ bit
X IX ɨ roses, rabbit
i IY i beat
o OW boat
O OY ɔɪ boy
U UH ʊ book
u UW u boot
UX[3] ʉ dude
Consonants[2]
ARPABET IPA Example
1-letter 2-letter
b B b buy
C CH China
d D d die
D DH ð thy
F DX ɾ butter
L EL bottle
M EM rhythm
N EN button
f F f fight
g G ɡ guy
h HH or H[3] h high
J JH jive
k K k kite
l L l lie
m M m my
n N n nigh
G NX or NG[3] ŋ sing
NX[3] ɾ̃ winter
p P p pie
Q Q ʔ uh-oh
r R ɹ rye
s S s sigh
S SH ʃ shy
t T t tie
T TH θ thigh
v V v vie
w W w wise
H WH ʍ why (without wine–whine merger)
y Y j yacht
z Z z zoo
Z ZH ʒ pleasure
Stress and auxiliary symbols[2]
AB Description
0 No stress
1 Primary stress
2 Secondary stress
3... Tertiary and further stress
- Silence
! Non-speech segment
+ Morpheme boundary
/ Word boundary
# Utterance boundary
: Tone group boundary
:1 or . Falling or declining juncture
:2 or ? Rising or internal juncture
:3 or . Fall-rise or non-terminal juncture

TIMIT

edit

In TIMIT, the following symbols are used in addition to the ones listed above:[4]

Symbol IPA Example Description
AX-H ə̥ suspect Devoiced /ə/
BCL obtain [b] closure
DCL width [d] closure
ENG ŋ̍ Washington Syllabic [ŋ]
GCL ɡ̚ dogtooth [ɡ] closure
HV ɦ ahead Voiced /h/
KCL doctor [k] closure
PCL accept [p] closure
TCL catnip [t] closure
PAU Pause
EPI Epenthetic silence
H# Begin/end marker

See also

edit

References

edit
  1. ^ a b Klautau, Aldebaro (2001). "ARPABET and the TIMIT alphabet" (PDF). Archived from the original (PDF) on June 3, 2016. Retrieved September 8, 2017.
  2. ^ a b c Rice, Lloyd (April 1976). "Hardware & software for speech synthesis". Dr. Dobb's Journal of Computer Calisthenics & Orthodontia. 1 (4): 6–8.
  3. ^ a b c d e Jurafsky, Daniel; Martin, James H. (2000). Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. Prentice Hall. pp. 94–5. ISBN 0-1309-5069-6.
  4. ^ "Table of all the phonemic and phonetic symbols used in the TIMIT lexicon". Linguistic Data Consortium. October 12, 1990. Retrieved September 8, 2017.
edit