Abstract

In this paper, the development of Multilingual Phone Recognition System (MPRS) in the context of Indian languages is described. MPRS is a language independent Phone Recognition System (PRS) that could recognise the phonetic units present in a speech utterance of any language. We have developed two Bilingual and a quadrilingual PRS using four Indian languages — Kannada, Telugu, Bengali, and Odia. International phonetic alphabets based transcription is used for grouping the acoustically similar phonetic units from multiple languages. Indian languages are analysed at two broad groups namely — Dravidian languages and Indo-Aryan languages. Bilingual PRSs are developed based on the grouping of Dravidian and Indo-Aryan languages. The performance of MPRSs is analysed and compared with that of monolingual PRSs. The advantages o MPRSs over monolingual PRSs are described. Further, we have developed tandem MPRSs using tandem features to improve the performance of the baseline MPRSs. It is observed that the performance of tandem MPRSs outperforms the performance of baseline monolingual PRSs in most of the cases.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call