ABSTRACT
Emotion recognition from acoustic signals plays a vital role in the field of audio and speech processing. Speech interfaces offer humans an informal and comfortable means to communicate with machines. Emotion recognition from speech signals has a variety of applications in the area of human computer interaction (HCI) and human behavior analysis. In this work, we develop the first emotional speech database of the Urdu language. We also develop the system to classify five different emotions: sadness, happiness, neutral, disgust, and anger using different machine learning algorithms. The Mel Frequency Cepstrum Coefficient (MFCC), Linear Prediction Coefficient (LPC), energy, spectral flux, spectral centroid, spectral roll-off, and zero-crossing were used as speech descriptors. The classification tests were performed on the emotional speech corpus collected from 20 different subjects. To evaluate the quality of speech emotions, subjective listing tests were conducted. The recognition of correctly classified emotions in the complete Urdu emotional speech corpus was 66.5% with K-nearest neighbors. It was found that the disgust emotion has a lower recognition rate as compared to the other emotions. Removing the disgust emotion significantly improves the performance of the classifier to 76.5%.
ABSTRACT
Past studies suggested that during early lactation and the transition period, higher plasma growth hormone (GH) levels in subclinical ketosis (SCK) might involve the initiation of body adipose tissues mobilization, resulting in metabolic disorders in ruminants particularly hyperketonemia. The upregulated GH mRNA expression in adipose tissue may take part in the adipolysis process in SCK-affected cows that paves a way for study further. This study aimed to characterize the plasma levels of GH, ß-hydroxybutyrate acid (BHBA) and non-esterified fatty acid (NEFA) and glucose (GLu) in ketotic cows and healthy control (CON) cows; to measure the liver function test (LFT) indices in ketotic and healthy CON cows, and finally the quantitative real-time PCR (qRT-PCR) assay of candidate genes expressed in adipose tissues of ketotic and healthy CON cows during 0 to 7 week postpartum. Three experiments were conducted. Experiment-1 involved 21 Holstein cows weighing 500-600 kg with 2-5 parities. Results showed that GH, BHBA, and NEFA levels in ketotic cows were significantly higher and the GLu level significantly lower. Pearson's correlation analysis revealed a significant positive correlation of GH with BHBA, NEFA, and GLu in ketotic and healthy CON cows. In experiment-2, dynamic monitoring of LFT indices namely, alanine aminotransferase (ALT), aspartate aminotransferase (AST), γ-glutamyl transpeptidase (GGT), total bilirubin (TBIL), direct bilirubin (DBIL), total protein (TP), albumin (ALB), globulin (GLOB) and albumin/globulin (A/G) were examined. The TBIL, DBIL, and GGT indices were significantly higher in ketotic cows and TP was significantly lower. In experiment-3, mRNA expression levels of GHR and peroxisome-proliferator-activated receptor alpha (PPARα) genes in adipose tissue were significantly upregulated in ketotic cows. However, the mRNA expression of insulin-like growth factor-I (IGF-1), insulin-like growth factor-I receptor (IGF-1R), and sterol regulatory element-binding protein-1c (SREBP-1c) genes in adipose tissue were downregulated in ketotic cows. Our study concluded that during postpartum, higher plasma GH levels in SCK cows might involve the initiation of body adipose tissue mobilization, resulting in hyperketonemia.
