Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: Arabic

Sortuj według:

Ogranicz wyniki do:

Medial Vowel Temporal Acoustics in Arabic and Japanese Polysyllabic Words

Aldholmi Yahya

Archives of Acoustics

2022

Vol. 47, No. 3

319--329

The current study is dedicated to measuring vowel temporal acoustics (duration, durational difference, and durational ratio) in the medial position of mostly CVCVCV polysyllabic words in Arabic and Japanese, avoiding the asymmetries in vowel position, syllable structure, and coda consonant quantity (singleton versus geminate) observed in previous experiments. Twenty-nine (16 Arabic and 13 Japanese) participants were asked to use a carrier sentence to produce 60 polysyllabic (mainly CVCVCV) items that contrasted in vowel quantity (short versus long) and vowel quality (/a/, /i/, and /u/) at a normal speech rate. The results show that while short and long vowels are durationally distinct within a language, Japanese vowels are clearly longer than Arabic vowels, although the durational difference remains approximately the same between the two languages. The durational ratio of short-to-long vowel presents a new pattern that contrasts with that reported in earlier research. Specifically, Japanese long vowels in the medial position of polysyllabic words are twice as long as their short counterparts, while Arabic long vowels are more than twice as long. This shows that both vowel position and syllable structure must be considered when measuring vowel temporal acoustics or when structuring stimuli for perception experiments.

Two template matching approaches to Arabic, Amharic and Latin isolated characters recognition

Cowell J., Hussain F.

Machine Graphics and Vision

2005

Vol. 14, No. 2

213-232

With the establishment of commercial OCR systems for Latin text, recent research efforts have been directed at the design of recognition systems for non-Latin scripts, such as Japanese, Cyrillic, Chinese, Hindi, Tibetan, and in particular Arabic. The Unicode 4.0 standard supports 50 scripts that are used across the world, and many, such as Amharic (Ethiopic), have attracted virtually no attention from researchers. An extensive literature review reveals no papers which report on an OCR system for Amharic. This paper describes a normalised technique which can be used for recognition of isolated Arabic, Amharic and Latin characters. Two approaches are considered for identifying the characters by comparing them to a series of templates and using a signature template scheme. The degrees of similarity between pairs of Amharic, Arabic and typical Latin characters are presented in the confusion matrix, and the performance of the two approaches is compared for each of these three character sets.