Browsing by Author "Reddy, N."

Now showing 1 - 5 of 5

Dravidian language classification from speech signal using spectral and prosodic features
(2017) Koolagudi, S.G.; Bharadwaj, A.; Srinivasa, Murthy, Y.V.; Reddy, N.; Rao, P.
The interesting aspect of the Dravidian languages is a commonality through a shared script, similar vocabulary, and their common root language. In this work, an attempt has been made to classify the four complex Dravidian languages using cepstral coefficients and prosodic features. The speech of Dravidian languages has been recorded in various environments and considered as a database. It is demonstrated that while cepstral coefficients can indeed identify the language correctly with a fair degree of accuracy, prosodic features are added to the cepstral coefficients to improve language identification performance. Legendre polynomial fitting and the principle component analysis (PCA) are applied on feature vectors to reduce dimensionality which further resolves the issue of time complexity. In the experiments conducted, it is found that using both cepstral coefficients and prosodic features, a language identification rate of around 87% is obtained, which is about 18% above the baseline system using Mel-frequency cepstral coefficients (MFCCs). It is observed from the results that the temporal variations and prosody are the important factors needed to be considered for the tasks of language identification. 2017, Springer Science+Business Media, LLC.
Dravidian language classification from speech signal using spectral and prosodic features
(Springer New York LLC barbara.b.bertram@gsk.com, 2017) Koolagudi, S.G.; Bharadwaj, A.; Vishnu Srinivasa Murthy, Y.V.; Reddy, N.; Rao, P.
The interesting aspect of the Dravidian languages is a commonality through a shared script, similar vocabulary, and their common root language. In this work, an attempt has been made to classify the four complex Dravidian languages using cepstral coefficients and prosodic features. The speech of Dravidian languages has been recorded in various environments and considered as a database. It is demonstrated that while cepstral coefficients can indeed identify the language correctly with a fair degree of accuracy, prosodic features are added to the cepstral coefficients to improve language identification performance. Legendre polynomial fitting and the principle component analysis (PCA) are applied on feature vectors to reduce dimensionality which further resolves the issue of time complexity. In the experiments conducted, it is found that using both cepstral coefficients and prosodic features, a language identification rate of around 87% is obtained, which is about 18% above the baseline system using Mel-frequency cepstral coefficients (MFCCs). It is observed from the results that the temporal variations and prosody are the important factors needed to be considered for the tasks of language identification. © 2017, Springer Science+Business Media, LLC.
Experimental Studies on Mechanical and Failure Behaviour of Single Lap Joints of Woven Jute-Hemp Fabric Reinforced Polymeric Composite Laminates
(SAE International, 2024) Koppad, P.; Chinnakurli Suryanarayana, R.; Reddy, N.; Sethuram, D.
In the aerospace industry, large aircrafts employ composite materials for making complex structures which not only reduces weight and cost but also reduces the number of joints. Irrespective of that joining of structures cannot be avoided and for that mechanical fasteners such as rivets and bolts are employed along with adhesive bonding. Further, in recent years natural fibers have been studied extensively for their numerous advantages and have already been made into several automotive applications. Keeping these current trends in mind an attempt is made to investigate the joining behavior of natural fiber composites experimentally. So in this study, the ultimate failure load, bearing strength and the dominating failure mode of jute-hemp fabric-reinforced polymeric composites joined using single and double-bolted configurations are studied. The polymeric composite laminates were successfully fabricated using resin infusion technique and test specimens were fabricated following ASTM D5961M-10 standard. The ultimate failure load for a double-bolted joint configuration was almost twice that of a single-bolted joint configuration. The failure analysis conducted using a scanning electron microscope revealed net tension as the main failure mode for both cases of bolted joints. Â© 2024 SAE International. All Rights Reserved.
Synthesis of high hardness, low COF diamond-like carbon using RF-PECVD at room temperature and evaluating its structure using electron microscopy
(2017) Ankit, K.; Varade, A.; Reddy, N.; Dhan, S.; Chellamalai, M.; Krishna, P.; Balashanmugam, N.
Diamond-like carbon (DLC) coatings have been deposited on Silicon wafers using a Radio Frequency based Plasma Enhanced Chemical Vapor Deposition (RF-PECVD) at room temperature. Experiments were carried out using a flow rate of 100 sccm and 300 sccm of acetylene (C2H2) gas and the bias voltage was varied from 300 to 450 V for DLC deposition. Scanning electron microscope (SEM) and transmission electron microscope (TEM) has been used to study the structure and morphology of the DLC coating. TEM results of DLC coatings deposited at 100 sccm C2H2 flow suggest that some crystalline features of diamond are present in the disordered matrix of DLC. Mechanical properties of DLC coatings were studied using a nanoindenter. The results indicate that the hardest DLC film is obtained at 100 sccm flow rate of C2H2 deposited at 450 V bias voltage of about 32.25 GPa. The results also indicate that the lowest coefficient of friction (COF) of about 0.04 in DLC film is obtained at 300 sccm flow rate of C2H2 deposited at 400 V bias voltage. COF is found to be lower in high C2H2 flow rate, wherever relatively softer DLC was deposited. 2017 Elsevier B.V.
Synthesis of high hardness, low COF diamond-like carbon using RF-PECVD at room temperature and evaluating its structure using electron microscopy
(Elsevier Ltd, 2017) Krishna, K.; Varade, A.; Reddy, N.; Dhan, S.; Chellamalai, M.; Krishna, P.; Balashanmugam, N.
Diamond-like carbon (DLC) coatings have been deposited on Silicon wafers using a Radio Frequency based Plasma Enhanced Chemical Vapor Deposition (RF-PECVD) at room temperature. Experiments were carried out using a flow rate of 100 sccm and 300 sccm of acetylene (C2H2) gas and the bias voltage was varied from 300 to 450 V for DLC deposition. Scanning electron microscope (SEM) and transmission electron microscope (TEM) has been used to study the structure and morphology of the DLC coating. TEM results of DLC coatings deposited at 100 sccm C2H2 flow suggest that some crystalline features of diamond are present in the disordered matrix of DLC. Mechanical properties of DLC coatings were studied using a nanoindenter. The results indicate that the hardest DLC film is obtained at 100 sccm flow rate of C2H2 deposited at 450 V bias voltage of about 32.25 GPa. The results also indicate that the lowest coefficient of friction (COF) of about 0.04 in DLC film is obtained at 300 sccm flow rate of C2H2 deposited at 400 V bias voltage. COF is found to be lower in high C2H2 flow rate, wherever relatively softer DLC was deposited. © 2017 Elsevier B.V.