Online ISSN: 2412-2599
Print ISSN: 2413-8835
Print ISSN: 2413-8835
Quarterly Published (4 Issues Per Year)
Volume 9 Number 2 June 2023
Morphological Differentiation and Karyotypic Studies of the African Common Toad Sclerophrys (Bufo) Regularis (Reuss, 1833)
Authors: Adewale A. Sorungbe ; Mobolanle Oladipupo Oniya ; Benjamin Oluwole Akinyele ; Olusola Olasumbo Odeyemi
The study analyzed the morphological differentiation and karyotype among populations of the common toad, Sclerophrys (Bufo) regularis from six Local Government Areas in Ondo state. Variations in fifteen morphometric and qualitative characters in one hundred and seventy-one animals from six population samples were analyzed using univariate and multivariate statistics. Descriptives of sexes and correlation between morphological characters was also analyzed. Female toads had larger mean values of most of the morphological characters studied with weight contributing the largest variance. The chromosomes of twenty-four specimens of the toad were also studied using standard bone marrow smear techniques. A chromosome complement of 2n=20 was observed for this species. The chromosomes consists of nine pairs of metacentric and one pair of submetacentric chromosomes. The chromosomes based on centromeric position could be grouped into two - metacentric and submetacentric - and based on size, into three metacentric chromosomes; 1-4 which were large, metacentric chromosomes; 5-6 medium sized metacentric chromosomes, while 7-9 were small sized, and the last pair (10), submetacentric chromosomes were small. The fundamental number of this species is 40 and with no sex chromosomes or satellites reported, while bi-armed chromosomes were observed. Findings also showed that female individuals of the species weighed more than the male.
Improving the Accuracy of Speech Recognition Models for Non-Native English Speakers using Bag-of-Words and Deep Neural Networks
Authors: Van-An Tran ; Dinh-Son Le ; Ha Huy Hung ; Dinh- Quan Nguyen
This letter presents a novel error correction module using a Bag-of-Words model and deep neural networks to improve the accuracy of cloud-based speech-to-text services on recognition tasks of non-native speakers with foreign accents. The Bag-of-Words model transforms text into input vectors for the deep neural network, which is trained using typical sentences in the curriculum for elementary schools in Vietnam and the Google Speech-to-Text data for those sentences. The trained network is then used for real-time error correction on a humanoid robot and yields 18% better accuracy than Google Speech-to-Text.