 |
Claims  |
|
|
What is claimed is:
1. A method for determining if any of a plurality of language groups may be
identified, or removed from consideration, as a language group of origin
for an input word using a programmable computer, the method comprising the
steps of:
(a) applying a set of filter rules, which are stored in memory means of the
programmable computer, to predetermined substrings of graphemes of the
input word to determine if there is a match between one of the substrings
and one of the filter rules of a particular language group which
positively identifies the input word as being part of a that language
group, or if there is an absence of a match between any of the
predetermined substrings of graphemes of the input word and the filter
rules for a particular language group of the plurality of language groups
so as to eliminate that particular language group from consideration as a
language group of origin of the input word, with the filter rules for each
language group of the plurality of language groups including N graphemes
where 1<N.ltoreq.R and R=the number of graphemes in the input word; and
(b) generating a representative indicator of the language group of origin
of the input word if there is a match or generating a list of possible
language groups of origin for the input word according to the filter rules
when there is the absence of a match.
2. The method as recited in claim 1, wherein the applying step includes
searching the filter rules from top to bottom and right to left.
3. A method for generating correct phonemics for an input word according to
a language group of origin using a programmable computer, the method
comprising the steps of:
(a) inputting the input word to the programmable computer;
(b) searching a dictionary stored in memory means of the programmable
computer for a match between the input word and a dictionary entry, with
each dictionary entry including a word and phonemics for that word, and
sending contents of a dictionary entry in which the word of that entry
matches the input word to a voice realization means for pronunciation, or
processing the input word according to the step (c) if there is an absence
of a match between the input word and a dictionary entry;
(c) applying a set of filter rules, which are stored in memory means of the
programmable computer, to predetermined substrings of graphemes of the
input word, with the filter rules for each language group of the plurality
of language groups including N graphemes where 1<N.ltoreq.R and R=the
number of graphemes in the input word, and with the applying step being
for,
(1) determining if there is a match between one of the predetermined set of
graphemes of the input word substrings and one of the filter rules
identifiable with one of the plurality of language groups which positively
identifies the input word as being part of a particular language group and
thereafter processing input word according to step (d), or
(2) determining if there is an absence of a match between any of the
predetermined substrings of graphemes of the input word and the filter
rules for a particular language group of the plurality of language groups
so as to eliminate that particular language group from consideration as a
language group of origin of the input word and if there is the absence of
match, generating a list of possible language groups of origin of the
input word, and thereafter processing the input word according to step
(e);
(d) transmitting the input word and a language tag indicative of the
language group of origin identified at substep (c) (1) to a
letter-to-sound means in the programmable computer, with the
letter-to-sound means including letter-to-sound rules, and further
processing the input word according to step (g);
(e) transmitting the input word and the list of possible language groups of
origin of the input word to a grapheme analyzer in the programmable
computer and determining a most probable language group of origin from the
list generated at substep (c) (2) by examining graphemes of the input word
of a predetermined length;
(f) transmitting the input word and the most probable language group of
origin determined at step (e) to the letter-to-sound means;
(g) generating in the letter-to-sound means according to the
letter-to-sound rules segmental phonemics for the input word and further
processing the input word according to step (h);
(h) transmitting the segmental phonemics and a language tag to a stress
assignment means of the programmable computer and generating in the stress
assignment means stress assignment information for the input word; and
(i) transmitting the segmental phonemics and the stress assignment
information to the voice realization means.
4. The method as recited in claim 3, wherein the graphemes of a
predetermined length are trigrams.
5. The method as recited in claim 3, wherein step (e) further includes
computing probabilities for graphemes of the input word being from a
particular language group according to Bayes' Rule.
6. The method as recited in claim 3, wherein the method further comprises
selecting a predetermined default pronunciation if the most probable
language group of origin determined at step (e) has a probability below a
predetermined threshold.
7. The method as recited in claim 3, wherein the method further comprises
selecting a predetermined default pronunciation if the most probable
language group of origin determined at step (e) has a probability that
exceeds a probability of a next most probable group of origin by less than
a predetermined amount.
8. An apparatus that is capable of being embodied in a programmable
computer for determining if any of a plurality of language groups may be
identified, or removed from consideration, as a language group of origin
for a given word, comprising:
filter rule store means for storing filter rules;
comparator means that are used for determining if there is a match between
a predetermined substring of graphemes of an input word and one of the
filter rules identifiable with one of a plurality of language groups which
positively identifies the input word as being part of a specific language
group, or if there is an absence of a match between any of the
predetermined substrings of graphemes of the input word and the filter
rules of a particular language group of the plurality of language groups
so as to eliminate that particular language group from consideration as a
language group from consideration as a language group of origin of the
input word, with the filter rules for each language group of the plurality
of language groups including N graphemes where 1 <N.ltoreq.R and R=the
number of graphemes in the input word; and
output means of the comparator means for outputting therefrom at least a
list of possible language groups of origin if there is an absence of a
match between a predetermined substring of graphemes and the input word,
or the language group of origin if there is a match between a
predetermined substring of graphemes and the input word.
9. A method for processing an input word before trigram analysis for
determining if any of a plurality of language groups may be identified, or
eliminated from consideration, as a language group of origin for the input
word, the method comprising applying a set of filter rules, which are
stored in memory means of a programmable computer, to predetermined
substrings of graphemes of the input word to determine if there is a match
between one of the substrings and one of the filter rules identifiable
with one of the plurality of language groups which positively identifies
the input word as being part of a specific language group, or if there is
an absence of a match between any of the predetermined substrings of
graphemes of the input word and the filter rules for a particular language
group of the plurality of language groups so as to eliminate that
particular language group from consideration as a language group of origin
of the input word, with the filter rules for each language group of the
plurality of language groups including N graphemes where
1.ltoreq.N.ltoreq.R and R =the number of graphemes in the input word. |
|
 |
|
 |
Claims |
|
|
|
Description |
|
|
FIELD OF THE INVENTION
The present invention relates to text-to-speech conversion by a computer,
and specifically to correctly pronouncing proper names from text.
BACKGROUND OF THE INVENTION
Name pronunciation may be used in the area of field service within the
telephone and computer industries. It is also found within larger
corporations having reverse directory assistance (number to name) as well
as in text-messaging systems where the last name field is a common entity.
There are many devices commercially available which synthesize American
English speech by computer. One of the functions sought for speech
synthesis which presents special problems is the pronunciation of an
unlimited number of ethnically diverse surnames. Due to the extremely
large number of different surnames in an ethnically diverse country such
as the United States, the pronouncing of a surname cannot be practically
implemented at present by use of other voice output technologies such as
audiotape or digitized stored voice.
There is typically an inverse relation between the pronunciation accuracy
of a speech synthesizer in its source language and the pronunciation
accuracy of the same synthesizer in a second language. The United States
is an ethnically heterogeneous and diverse country with names deriving
from languages which range from the common Indo-European ones such as
French, Italian, Polish, Spanish, German, Irish, etc. to more exotic ones
such as Japanese, Armenian, Chinese, Arabic, and Vietnamese. The
pronunciation of surnames from the various ethnic groups does not conform
to the rules of standard American English. For example, most Germanic
names are stressed on the first syllable, whereas Japanese and Spanish
names tend to have penultimate stress, and French names, final stress.
Similarly, the orthographic sequence CH is pronounced [c]; in English
names (e.g. CHILDERS), [s] in French names such as CHARPENTIER, and [k] in
Italian names such as BRONCHETTI. Human speakers often provide correct
pronunciation by "knowing" the language of origin of the name. The problem
faced by a voice synthesizer is speaking these names using the correct
pronunciation, but since computers do not "know" the ethnic origin of the
name, that pronunciation is often incorrect.
A system has been proposed in the prior art in which a name is first
matched against a number of entries in a dictionary which contains the
most common names from a number of different language groups. Each
dictionary entry contains an orthographic form and a phonetic equivalent.
If a match occurs, the phonetic equivalent is sent to a synthesizer which
turns it into an audible pronunciation for that name.
When the name is not found in the dictionary, the proposed system used a
statistical trigram model. This trigram analysis involved estimating a
probability that each three letter sequence (or trigram) in a name is
associated with an etymology. When the program saw a new word, a
statistical formula was applied in order to estimate for each etymology a
probability based on each of the three letter sequences (trigrams) in the
word.
The problem with this approach is the accuracy of the trigram analysis.
This is because the trigram analysis computes only a probability, and with
all language groups being considered as a possible candidate for the
language group of origin of a word, the accuracy of the selection of the
language group of origin of the word is not as high as when there are
fewer possible candidates.
SUMMARY OF THE INVENTION
The present invention solves the above problem by improving the accuracy of
the trigram analysis. This is done by providing a filter which either
positively identifies a language group as the language group of origin, or
eliminates a language group as a language group of origin for a given
input word. The filtering method according to the present invention
comprises identifying or eliminating a language group as a language group
of origin for an input word according to a stored set of filter rules. The
step of identifying or eliminating a language group includes performing an
exhaustive search of the rule set using a right-to-left scan. Language
groups are eliminated when a match of one of these substrings to one of
the filter rules indicates that a language group should be eliminated from
consideration as the language group of origin for the input word. This is
done until a match of one of the substrings to one of the rules positively
identifies a language group. When no language group is positively
identified as a language group of origin after all of the substrings for a
given input word are compared, a list of possible language groups of
origin is produced. This filter method also produces a positively
identified language group of origin when there is a positive
identification.
The advantages of using a filter before the trigram analysis includes
avoiding unnecessary trigram analysis when filter rules can positively
identify a language group as a language group of origin. When no language
group can be positively identified, the filtering method also reduces the
chances of an incorrect guess being made in the trigram analysis by
reducing the number of possible language groups in consideration as the
language group of origin. Through the elimination of some language groups,
the identification of a language group of origin is more accurate, as
discussed above.
The invention also includes a method for generating correct phonemics for a
given input word according to the language group of origin of the input
word. This method comprises searching a dictionary for an entry
corresponding to an input word, each entry containing a word and phonemics
for that word. This entry is then sent to a voice realization unit for
pronunciation when the dictionary search reveals an entry corresponding to
the input word. The input word is sent to a filter when the input word
does not have a corresponding entry in the dictionary.
The next step in the method involves filtering to identify a language group
of origin for the input word or to eliminate at least one language group
of origin for the input word. When the filter positively identifies a
language group of origin for the input word, the input word and a language
tag indicating a language group of origin for the input word is sent from
the filter to a letter-to-sound module. When a language group of origin is
not positively identified by the filter, the input word and any language
groups not eliminated are sent from the filter to a trigram analyzer.
A most probable language group of origin for the input word is produced by
analyzing trigrams occurring in the input word. This most probable
language group of origin produced by the trigram analysis is sent along
with the input word to a subset of letter-to-sound rules that correspond
to the most probable language group. Phonemics are generated for the input
word according to the corresponding subset of letter-to-sound rules.
BRIEF DESCRIPTION OF THE DRAWINGS
FIG. 1 illustrates a logic block diagram of language identification and
phonemics realization modules.
FIG. 2 shows a logic block diagram of a name analysis system containing the
language group identification and phonemic realization module of FIG. 1,
constructed in accordance with the present invention.
DETAILED DESCRIPTION
FIG. 1 is a diagram illustrating the various logic blocks of the present
invention. The physical embodiment of the system can be realized by a
commercially available processor logically arranged as shown.
A name to be pronounced is accepted as an input. The search is made through
entries in a dictionary 10 for this input name. Each dictionary entry has
a name and phonemics for that name. A semantic tag identifies the word as
being a name.
A search for an input name that corresponds to an entry in the dictionary
10 results in a hit. The dictionary 10 will then immediately send the
entry (name and phonemics) to a voice realization unit 50, which
pronounces the name according to the phonemics contained in the entry. The
pronunciation process for that input word would then be complete.
A dictionary miss occurs when there is no entry corresponding to the input
name in the dictionary 10. In order to provide the correct pronunciation,
the system attempts to identify the language group of origin of the input
name. This is done by sending to a filter 12 the input name which missed
in the dictionary 10. The input name is analyzed by the filter 12 in order
to either positively identify a language group or eliminate certain
language groups from further consideration.
The filter 12 operates to filter out language groups for input names based
on a predetermined set of rules. These rules are provided to the filter 12
by a rule store described later.
Each input name is considered to be composed of a string of graphemes. Some
strings within an input name will uniquely identify (or eliminate) a
language group for that name. For example, according to one rule the
string BAUM positively identifies the input name as German, (e.g.
TANNENBAUM). According to another rule the string MOTO at the end of a
name positively identifies the language group as Japanese (e.g. KAWAMOTO).
When there is such a positive identification, the input name and the
identified language group (L TAG) are sent directly to a letter-to-sound
section 20 that provides the proper phonemics to the voice realization
unit 50.
The filter 12 otherwise attempts to eliminate as many language groups as
possible from further consideration when positive identification is not
possible. This increases probability accuracy of the remaining analysis of
the input name. For example, a filter rule provides that if the string -B
is at the end of a name, language groups such as Japanese, Slavic, French,
Spanish and Irish can be eliminated from further consideration. By this
elimination, the following analysis to determine the language group of
origin for an input name not positively identified is simplified and
improved.
Assuming that no language group can be positively identified as the
language group of origin by the filter 12, further analysis is needed.
This is performed by a trigram analyzer 14 which receives the input name
and filter 12. The trigram analyzer 14 parses the string of graphemes (the
input name) into trigrams, which are grapheme strings that are three
graphemes long. For example, the grapheme string #SMITH# is parsed into
the following five trigrams: #SM, SMI, MIT, ITH, TH#. For trigram
analysis, the pound-sign (word-boundary) is considered a grapheme.
Therefore, the number of trigrams is always the same as the number of
graphemes in the name.
The probability for each of the trigrams being from a particular language
group is input to the trigram analyzer 14. This probability, computed from
an analysis of a name data base, is received as an input from a frequency
table of trigrams for each language group that was not eliminated by the
filter 12. The same thing is also done for each of the other trigrams of
the grapheme string.
The following (partial) matrix shows sample probabilities for the surname
VITALE:
______________________________________
Li Lj . . . Ln
______________________________________
#VI .0679 .4659 .2093
VIT .0263 .4145 .0000
ITA .0490 .7851 .0564
TAL .1013 .4422 .2384
ALE .0867 .2602 .2892
LE# .1884 .3181 .0688
Total .0866 .4477 .1437
Prob.
______________________________________
In the array above, L is a language group and n is the number of language
groups not eliminated by the filter 12. The trigram #VI has a probability
of 0.0679 of being from language group Li, 0.4659 of being from the
language group Lj and 0.2093 of being from language group Ln. Lj is
averaged as the highest probability and thus the language group is
identified.
The probability of each of the trigrams of the grapheme string (input name)
is similarly input to the trigram analyzer 14. The probability of each
trigram in an input name is averaged for each language group. This
represents the probability of the input name originating from a particular
language group. The probability that the grapheme string #VITALE# belongs
to a particular language group is produced as a vector of probabilities
from the total probability line. From this vector of probabilities, other
items such as standard deviation and thresholding can also be calculated.
This ensures that a single trigram cannot overly contribute to or distort
the total probability.
Although the illustrated embodiment analyzes trigrams, the analyzer 14 can
be configured to analyze different length grapheme strings, such as
two-grapheme or four-grapheme strings.
In the example above, the trigram analyzer 14 shows that language group
L.sub.j is the most probable language group of origin for the given input
name, since it has the highest probability. It is this most probable
language group that becomes the L TAG for the input name. The L TAG and
the input name are then sent to the letter-to-sound section 20 to produce
the phonemics for the input.
The filter rules are constructed in such a way that ambiguity of
identification is not possible. That is, a language may not be both
eliminated and positively identified since a dominance relationship
applies such that a positive identification is dominant over an
elimination rule in the unlikely event of a conflict.
Similarly, a language group may not be positively identified for more than
one language because the filter rules constitute an ordered set such that
the first positive identification applies.
The system may default to a certain language group if one of two
thresholding criteria is met: (a) absolute thresholding occurs when the
highest probability determined by the trigram analyzer 14 is below a
predetermined threshold Ti. This would mean that the trigram analyzer 14
could not determine from among the language groups a single language group
with a reasonable degree of confidence; (b) relative thresholding occurs
when the difference in probabilities between the language group identified
as having the highest probability and the language group identified as
having the second highest probability falls below a threshold Tj as
determined by the trigram analyzer 14.
The default to a specified language group is a settable parameter. In an
English-speaking environment, for example, a default to an English
pronunciation is generally the safest course since a human, given a low
confidence level, would most likely resort to a generic English
pronunciation of the input name. The value of the default as a settable
parameter is that the default would be changed in certain situations, for
example, where the telephone exchange indicates that a telephone number is
located in a relatively homogeneous ethnic neighborhood.
As mentioned earlier, the name and language tag (LTAG) sent by either the
filter 12 or the trigram analyzer 14 is received by the letter-to-sound
rule section 20. The letter-to-sound rule section 20 is broken up
conceptually into separate blocks for each language group. In other words,
language group (L.sub.i) will have its own set of letter-to-sound rules,
as does language group (L.sub.j), language group (L.sub.k) etc. to
language group (L.sub.n).
Assuming that the input name has been identified sufficiently so as not to
generate a default pronunciation, the input name is sent to the
appropriate language group letter-to-sound block 22.sub.i-n according to
the language tag associated with the input name.
In the letter-to-sound rule section 20, the rules for the individual
language group blocks 22 are subsets of a larger and more complex set of
letter-to-sound rules for other language groups including English. A
letter-to-sound block 22.sub.i for a specific language group L.sub.i that
has been identified as the language group of origin will attempt to match
the largest grapheme sequence to a rule. This is different from the filter
12 which searches top to bottom, and in this embodiment right to left, for
the string of graphemes in an input name that fits a filter rule. The
letter-to-sound block 22.sub.i-n for a specific language scans the
grapheme string from left to right or right to left, the illustrated
embodiment using a right to left scan.
An example of the letter-to-sound rules for a specific block L.sub.i can be
seen for a name such as MANKIEWICZ. This input name would be identified as
originating from the Slavic language group, having the highest
probability, and would therefore be sent to the Slavic letter-to-sound
rules block 22.sub.i. In that block 22.sub.i, the grapheme string -WICZ
has a pronunciation rule to provide the correct segmental phonemics of the
string. However, the grapheme string -KIEWICZ also has a rule in the
Slavic rule set. Since this is a longer grapheme string, this rule would
apply first. The segmental phonemics for any remaining graphemes which do
not correspond to a language specific pronunciation rule will then be
determined from the general pronunciation block. In this example, the
segmental phonemics for the graphemes M, A, and N would be determined
(separately) according to the general pronunciation rules. The
letter-to-sound block 22.sub.i sends the concatenated phonemics of both
the language-sensitive grapheme strings and the non-language-sensitive
grapheme strings together to the voice realization unit 50 for
pronunciation.
The filter 12 does not contain all of the larger strings which are language
specific that are in the letter-to-sound rules 20. The larger strings are
not all needed since, for example, the string-WICZ would positively
identify an input name as Slavic in origin. There is then no need for the
string -KIEWICZ filter rule, since -WICZ is a subset of -KIEWICZ and thus
would identify the input name.
The letter-to-sound module outputs the phonemics for names mainly in the
form of segmental phonemic information. The output of the letter-to-sound
rule blocks 22.sub.i-n serve as the input to stress sections 24.sub.i-n.
These stress sections 24.sub.i-n take the LTAG along with the phonemics
produced by individual letter-to-sound rule blocks 22.sub.i-n and output a
complete phonemic string containing both segmental phonemes (from
letter-to-sound rule blocks 22.sub.i-n) and the correct stress pattern for
that language For example, if the language identified for the name VITALE
was Italian, and letter-to-sound rule block 22 provided the phoneme string
[vitali], then the stress section 24.sub.i would place stress on the
penultimate syllable so that the final phonemic string would be [vitali].
It should be noted that the actual rules used in the filter 12, in the
letter-to-sound section 20, and the stress sections 24.sub.i-n are rules
which are either known or easily acquired by one skilled in the art of
linguistics.
The system described above can be viewed as a front end processor for a
voice realization unit 50. The voice realization unit 50 can be a
commercially available unit for producing human speech from graphemic or
phonemic input. The synthesizer can be phoneme-based or based on some
other unit of sound, for example diphone or demi-syllable. The synthesizer
can also synthesize a language other than English.
FIG. 2 shows a language group identification and phonetic realization block
60 as part of a system. The language group identification and phonetic
realization block 60 is made up of the functional blocks shown in FIG. 1.
As shown, the input to the language identification and phonetic
realization block 60 is the name, the filter rules and the trigram
probabilities. The output is the name, the language tag and phonemics,
which are sent to the voice realization unit 50. It should be noted that
phonemics means in this context, any alphabet of sound symbols including
diphones and demi-syllables.
The system according to FIG. 2 marks grapheme strings as belonging to a
particular language group. The language identifier is used to pre-filter a
new data base in order to refine the probability table to a particular
data base. The analysis block 62 receives as inputs the name and language
tag and statistics from the language identification and phonetic
realization block 60. The analysis block takes this information and
outputs the name and language tag to a master language file 64 and
produces rules to a filter rule store 68. In this way, the data base of
the system is expanded as new input names are processed so that future
input names will be more easily processed. The filter rule store 68
provides the filter rules to the filter 12 and the language identification
and phonetic realization block 60.
The master file contains all grapheme strings and their language group tag.
This block 64 is produced by the analysis block 62. The trigram
probabilities are arranged in a data structure 66 designed for ease of
searching for a given input trigram. For example, the illustrated
embodiment uses an N-deep three dimensional matrix where n is the number
of language groups.
Trigram probability tables are computed from the master file using the
following algorithm:
______________________________________
compute total number of occurrences of each trigram for
all language groups L (1-N);
for all grapheme strings S in L
for all trigrams T in S
if (count [T][L] = 0)
uniq [L] + = 1
count [T][L] + = 1
for all possible trigrams T in master
sum = 0
for all language groups L
sum + = count [T][L]/uniq[L]
for all language groups L
if sum >0,prob[T][L]=count [T] [L]/uniq[L]/sum
else prob[T][L]=0.0;
______________________________________
The trigram frequency table mentioned earlier can be thought of as a
three-dimensional array of trigrams, language groups and frequencies.
Frequencies means the percentage of occurrence of those trigram sequences
for the respective language groups based on a large sample of names. The
probability of a trigram being a member of a particular language group can
be derived in a number of ways. In this embodiment, the probability of a
trigram being a member of a particular language group is derived from the
well-known Bayes theorem, according to the formula set forth below:
Bayes' Rules states that the probability that Bj occurs given A,
P(Bj.vertline.A), is
##EQU1##
More specific to the problem, the probability a language group given a
trigram, T, is P(Li.vertline.T), where
##EQU2##
where X=number of times the token, T, occurred in the language group, Li
Y=number of uniquely occurring tokens in the language group, Li
P(L.sub.i)=1/N always
where N=number of language groups (nonoverlapping)
##EQU3##
The final table then has four dimensions; one for each grapheme of the
trigram, and one for the language group.
The trigram probabilities as computed by the block 66 are sent to the
language identification and phonetic realization block 60, and
particularly to the trigram analyzer 14 which produces the vector of
probabilities that the grapheme string belongs to a particular language
group.
Using the above-described system, names can be more accurately pronounced.
Further developments such as using the first name in conjunction with the
surname in order to pronounce the surname more accurately are
contemplated. This would involve expanding the existing knowledge base and
rule sets.
* * * * *
|
|
|
|
|
|
|
Description |
|
