Speaker recognition based on Arabic phonemes
| Autor: | Mansour Alsulaiman, Ghulam Muhammad, Awais Mahmood |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Linguistics and Language
Computer science Arabic Speech recognition computer.software_genre 01 natural sciences Language and Linguistics Speech segmentation 030507 speech-language pathology & audiology 03 medical and health sciences Phonetic search technology 0101 mathematics business.industry Communication 010102 general mathematics Pharyngeal consonant Speaker recognition language.human_language Computer Science Applications Speaker diarisation Modeling and Simulation language Computer Vision and Pattern Recognition Artificial intelligence 0305 other medical science Speaker recognition system business computer Software Natural language processing Utterance |
| Zdroj: | Speech Communication. 86:42-51 |
| ISSN: | 0167-6393 |
| DOI: | 10.1016/j.specom.2016.11.004 |
| Popis: | In this paper, we investigate the effect of Arabic phonemes on the performance of speaker recognition systems. The investigation reveals that some Arabic phonemes have a strong effect on the recognition rate of such systems. The performance of speaker recognition systems can be improved and their execution time can be reduced by utilizing this finding. Additionally, this finding can be used by segmenting the most effective phonemes for speaker recognition from the utterance, using only the segmented part of the speech for speaker recognition. It can also be used in designing the text to be used in high-performance speaker recognition systems. From our investigation, we find that the recognition rates of Arabic vowels were all above 80%, whereas the recognition rates for the consonants varied from very low (14%) to very high (94%), with the latter achieved by a pharyngeal consonant followed by the two nasal phonemes, which achieved recognition rates above 80%. Four more consonants had recognition rates between 70% and 80%. We show that by utilizing these findings and by designing the text carefully, we can build a high-performance speaker recognition system. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect