Arpabet

From Wikipedia, the free encyclopedia

Arpabet is a phonetic transcription code developed by Advanced Research Projects Agency (ARPA) as a part of their Speech Understanding Project (1971-1976). It represents each phoneme of General American English with a distinct sequence of ASCII characters. Arpabet has been used in several speech synthesizers, like SAM for the Commodore 64, Say for the Amiga and TextAssist for the PC. It is also used in the CMU Pronouncing Dictionary.

[edit] Symbols

In Arpabet, every phoneme is represented by one or two capital letters. Digits are used as stress indicators (the higher the digit value, the higher the stress) and are placed at the end of the stressed syllabic vowel. Punctuation marks are used like in the written language, to represent intonation changes at the end of clauses and sentences. The stress values are:

Value	Description
0	No stress
1	Primary stress
2	Secondary stress

The following codes are used to represent IPA characters:

Symbol	IPA
IY	iː
UW	uː
IH	ɪ
UH	ʊ
EH	ɛ
ER	ɝː
AH	ə
AE	æ
AO	ɔ
AO R	ɔr
AA R	ɑr
AA	ɑː
IH R	ɪr
UH R	ʊr
EY	eɪ
OW	oʊ
EH R	ɛr
OY	ɔɪ
AY	aɪ
AW	aʊ
P	p
B	b
T	t
CH	tʃ
D	d
JH	dʒ
K	k
G	ɡ
M	m
N	n
NG	ŋ
F	f
V	v
TH	θ
DH	ð
S	s
Z	z
SH	ʃ
ZH	ʒ
HH	h
R	r
Y	j
L	l
W	w