PRESENTED BY:-
VICKY AGARWAL

---

[attachment=12645]
WHY PHONETIC
Simple information searches -- name lookups, word searches, etc. -- are often implemented in terms of an exact match criterion. However, given both the diversity of homophonic (pronounced the same) words and names, as well as the propensity for humans to misspell surnames, this simplistic criterion often yields less than desirable results, in the form of reduced result sets, missing records that differ by a misplaced letter or different national spelling.
INTRODUCTION
Conception of a sound in the most neutral form possible and distinguishes between different words.
A phoneme is the theoretical representation of a sound .
Phonemes are mental abstractions of them.
A phonemically "perfect" alphabet is one that has a single symbol for each phoneme
RESTRICTED PHONEMES
It can only occur in a certain environment.
/ŋ/, as in sing, occurs only at the end of a syllable, never at the beginning.
/h/ occurs only before vowels and at the beginning of a syllable, never at the end.
Under most interpretations, /w/ and /j/ occur only before a vowel, never at the end of a syllable.
PHONOLOGY
Phonology is a subfield of linguistics which studies the sound system of a specific language.
It describes the way sounds function within a given language or across languages.
Is studying which sounds are distinctive units within a language.
PHONETIC MATCHING
When building solutions which perform searches of textual data given a search criteria, it is often desirable to account for the way in which the search terms are pronounced, compared to the pronunciation of the data being searched, producing as a result those records, which "sound like" the search terms. The algorithms by which it is performed are called "phonetic matching algorithms" or "phonetic encoding algorithms."
PHONETIC MATCHING ALGORITHMS
Soundex.
Metaphone.
Double Metaphone.
SOUNDEX
Soundex was developed by Robert Russell and Margaret Odell 1918 and 1922 and patented in 20th century.
Soundex is a Phonetic algorithm.
The Soundex code for a name consists of a letter followed by three numbers: the letter is the first letter of the name, and the numbers encode the remaining consonants
SOUNDEX ALGORITHM
Retain the first letter of the string.
Remove all occurrences of the following letters, unless it is the first letter: a, e, h, i, o, u, w, y .
Assign numbers to the remaining letters (after the first) as follows:
b, f, p, v = 1
c, g, j, k, q, s, x, z = 2
d, t = 3
l = 4
m, n = 5
r = 6.
If two or more letters with the same number were adjacent in the original name (before step 1), or adjacent except for any intervening h and w, then omit all but the first.
Return the first four characters, right-padding with zeroes if there are fewer than four.
Using this algorithm:- both "Robert" and "Rupert" return the same string "R163" while "Rubin" yields "R150".
METAPHONE
Metaphone was developed by Lawrence Philips in 1990, as a response to deficiencies in the Soundex algorithm.
it "understands" the basic rules of English pronunciation.
Metaphone is available as a built-in operator in a number of systems, including later versions of PHP.
The original author later produced a new version of the algorithm, which he named Double Metaphone.
DOUBLE METAPHONE
Its implementation was described in the June 2000 issue of C/C++ Users Journal.
It is called "Double" because it can return both a primary and a secondary code for a string.
It tries to account for myriad irregularities in English, Germanic, Greek, French, Italian, Spanish, Chinese, and other origin.
DOUBLE METAPHONE ALGORITHM
These algorithms attempt to detect phonetic ("sounds-like") relationships between words.
It works by producing one or possibly two phonetic keys given a word.
The primary key represents the American pronunciation of the source word.
The alternate key represents an alternate, national pronunciation. When an alternate is computed, it can be pivotal in matching the word.
Contd..
To compare two words for phonetic similarity, one computes their respective Double Metaphone keys, and then compares each combination:
Word 1 Primary - Word 2 Primary
Word 1 Primary - Word 2 Alternate
Word 1 Alternate - Word 2 Primary
Word 1 Alternate - Word 2 Alternate
Obviously if the keys in any of these comparisons are not produced for the given words, the comparisons involving those keys are not performed.
ADVANTAGES
Knowing the sound/symbol relationships.
Effective searches of proper names in databases and other collections.
The ability explicitly and segmentally of sound units smaller than the syllables.
DISADVANTAGES
Recognizing the language and then the distribution of characters within the particular language.
The problem is 30% don’t have the capacity to spell whole words and 50% can’t memorize well enough.
APPLICATIONS
Present-day scientific research stands much closer to industrial, clinical and educational applications.
Active Server Pages application, which presents a browser-based form prompting for a search term.
FUTURE SCOPE
Simple stationary signals to complex dynamic signals, from laboratory speech to natural speech.
Jnd(just noticable difference) and reduction.
A phonetician has to be aware of linguistic, communicative and multimodal aspects.
CONCLUSION
This article has explored the phonetic matching problem, introduced the algorithms as a candidate solution.
How to adapt this technology to a relational database system where the vast majority of information requiring phonetic searching is likely to be stored.