Research Article
Convolutional Neural Networks to Facilitate the Continuous Recognition of Arabic Speech with Independent Speakers
Table 6
Comparative WER results between this research and Abushariah et al. [
47].
| | Gaussian mixture distributions | Sphinx-4 recognizer | | This research (%) | Abushariah et al. [47] |
| | Gaussian 2 | 10.77 | — | | Gaussian 4 | 8.45 | — | | Gaussian 8 | 8.17 | — | | Gaussian 16 | 8.65 | 14.44% | | Gaussian 32 | 10.85 | — |
|
|
