Toward enhanced Arabic speech recognition using part of speech tagging

Abstract

One major source of suboptimal performance in automatic continuous speech recognition systems is misrecognition of small words. In general, errors resulting from small words are much more than errors resulting from long words. Therefore, compounding some words (small or long) to produce longer words is welcome by speech recognition decoders. In this paper, we present a novel approach to artificially generate compound words using part of speech tagging. For this purpose, we consider two cases in Arabic speech where two words are pronounced without a silence period in between: a noun followed by an adjective, and a preposition followed by any word. To collect the candidate compound words, we use Stanford Arabic tagger to tag all words in our baseline transcription corpus. Then, compound words are generated whenever any of the two cases occur in a sequence of two words. The unique compound words are then added to the expanded pronunciation dictionary, as well as to the language model. Using Sphinx 3, we test the proposed method for a 5.4 hours speech corpus of modern standard Arabic. The results show a significant improvement, as the word error rate is reduced by 2.39%.

Exploring the Performance of Tagging for the Classical and the Modern Standard Arabic

“…(ii) Enhancing the performance in speech recognition: [7] employs the PoS to generate new words based on the neighboring word tags. The study used compound nouns that are followed by adjectives and the preposition followed by any word.…”

Written Grammatical Errors of Arabic as Second Language (ASL) Learners: An Evaluative Study

“…However, some others disagreed with such ideas. They suggested introducing new artificial approaches that may help to enhance Arabic speech recognition by writers as well as speakers (Abu-Zeina et al, 2011) A new trend led by some researchers who resorted to study the mistakes made by advanced Second Language learners, claiming that this may help to fully understand their written mistakes which, in turn, may help researchers to take safeguards to guarantee that these written grammatical errors will not be committed again by novice learners (Başöz & Aydın, 2011). Those who disagreed with the above mentioned views thought that it is not enough to analyze the errors of these advanced second language learners.…”