Package nzilbb.encoding

Class DISC2ARPAbet

java.lang.Object

nzilbb.encoding.PhonemeTranslator

nzilbb.encoding.DISC2ARPAbet

All Implemented Interfaces:

Function<String,String>, UnaryOperator<String>

public class DISC2ARPAbet
extends PhonemeTranslator

Translates CELEX-DISC-encoded transcriptions like tr{nskrIpSVn to ARPAbet-encoded phonemic transcriptions like T R AE N S K R IH P SH AX N.

There are differences between the CMU2DISC translation and this one:

ARPAbet includes phonemes not in the CMU set:

'L'

"DX" - flap - this is an extension to DISC

'^'

"NX" - nasal flap - doesn't exist in DISC, we make it /n/

'?'

"TQ" - glottal stop - this is an extension to DISC

Also CMU2DISC strictly uses only phonemes in the CMU dictionary set, where the "ARPAbet" translation may also contain phonemes corresponding to those that exist in DISC but not in ARPAbet:

'F'

"EM" - e.g. idealism

'H'

"EN" - e.g. burden

'P'

"EL" - e.g. dangle

'C'

"UN" - e.g. bacon

'0'

"VN" - e.g. lingerie

'~'

"ON" - e.g. bouillon

'c'

"IM" - e.g. timbre

'q'

"IN" - e.g. detente

... and any other phones encountered that are in neither set are passed through unchanged.

Mapping

DISC		ARPAbet	Example
			Vowels
#	→	AA	START	odd/father
{	→	AE	TRAP	at/fast
V	→	AH	STRUT	hut/but
$	→	AO	THOUGHT	ought/fall - two-to-one
Q	→	AO	LOT	ought/off - two-to-one
6	→	AW	MOUTH	cow/how
@	→	AX	schwa	discuss
2	→	AY	PRICE	hide/my
E	→	EH	DRESS	Ed/red
3	→	ER	NURSE	hurt/her
1	→	EY	FACE	ate/say
I	→	IH	KIT	it/big
i	→	IY	FLEECE	eat/bee
5	→	OW	GOAT	oat/show
4	→	OY	CHOICE	toy/boy
U	→	UH	FOOT	hood/should
u	→	UW	GOOSE	two/you
			Consonants
b	→	B
J	→	CH
d	→	D
D	→	DH
f	→	F
g	→	G
h	→	HH
_	→	JH
k	→	K
l	→	L
m	→	M
n	→	N
N	→	NG
p	→	P
r	→	R
R	→	R		Possible linking R is pretty definitely R
s	→	S
S	→	SH
t	→	T
T	→	TH
v	→	V
w	→	W
j	→	Y
z	→	Z
Z	→	ZH
			Not in the CMU set but exist in Buckeye corpus
L	→	DX	flap	this is an extension to DISC
^	→	NX	nasal flap	doesn't exist in DISC, we make it /n/
?	→	TQ	glottal stop	this is an extension to DISC
			Not in CMU set but exist in DISC
7	→	IY R	NEAR
8	→	EH R	SQUARE
9	→	UH R	CURE
F	→	EM	idealism
H	→	EN	burden
P	→	EL	dangle
C	→	UN	bacon
0	→	VN	lingerie
~	→	ON	bouillon
c	→	IM	timbre
q	→	IN	detente

Author:

Robert Fromont robert@fromont.net.nz

See Also:

ARPAbet2DISC, CMU2DISC

Constructor Summary

Constructors

Constructor	Description
DISC2ARPAbet()	Default constructor.

Method Summary

Modifier and Type	Method	Description
String	apply(String source)	Translates a phonemic transcription from the source encoding to the destination encoding.

Methods inherited from class nzilbb.encoding.PhonemeTranslator

getDestinationEncoding, getSourceEncoding

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface java.util.function.Function

andThen, compose

Constructor Detail

DISC2ARPAbet

public DISC2ARPAbet()

Default constructor.

Method Detail

apply

public String apply(String source)

Translates a phonemic transcription from the source encoding to the destination encoding.

Specified by:

apply in interface Function<String,String>

Overrides:

apply in class PhonemeTranslator

Parameters:

source - Phonemic transcription in the source encoding.

Returns:

Phonemic transcription in the destination encoding.