Speech Query Recognition for Tamil Language Using Wavelet and Wavelet Packets

Iswarya, P.,Radha, V. Korea Information Processing Society 2017 Journal of information processing systems Vol.13 No.5

Speech recognition is one of the fascinating fields in the area of Computer science. Accuracy of speech recognition system may reduce due to the presence of noise present in speech signal. Therefore noise removal is an essential step in Automatic Speech Recognition (ASR) system and this paper proposes a new technique called combined thresholding for noise removal. Feature extraction is process of converting acoustic signal into most valuable set of parameters. This paper also concentrates on improving Mel Frequency Cepstral Coefficients (MFCC) features by introducing Discrete Wavelet Packet Transform (DWPT) in the place of Discrete Fourier Transformation (DFT) block to provide an efficient signal analysis. The feature vector is varied in size, for choosing the correct length of feature vector Self Organizing Map (SOM) is used. As a single classifier does not provide enough accuracy, so this research proposes an Ensemble Support Vector Machine (ESVM) classifier where the fixed length feature vector from SOM is given as input, termed as ESVM_SOM. The experimental results showed that the proposed methods provide better results than the existing methods.

Speech Query Recognition in Tamil Language Using Wavelet and Wavelet Packets

P. Iswarya,V. Radha 한국정보처리학회 2017 Journal of information processing systems Vol.13 No.5

Speech recognition is one of the fascinating fields in the area of Computer science. Accuracy of speechrecognition system may reduce due to the presence of noise present in speech signal. Therefore noise removalis an essential step in Automatic Speech Recognition (ASR) system and this paper proposes a new techniquecalled combined thresholding for noise removal. Feature extraction is process of converting acoustic signalinto most valuable set of parameters. This paper also concentrates on improving Mel Frequency CepstralCoefficients (MFCC) features by introducing Discrete Wavelet Packet Transform (DWPT) in the place ofDiscrete Fourier Transformation (DFT) block to provide an efficient signal analysis. The feature vector isvaried in size, for choosing the correct length of feature vector Self Organizing Map (SOM) is used. As asingle classifier does not provide enough accuracy, so this research proposes an Ensemble Support VectorMachine (ESVM) classifier where the fixed length feature vector from SOM is given as input, termed asESVM_SOM. The experimental results showed that the proposed methods provide better results than theexisting methods.

Speech Query Recognition for Tamil Language Using Wavelet and Wavelet Packets

( P. Iswarya ),( V. Radha ) 한국정보처리학회 2017 Journal of information processing systems Vol.13 No.5

Speech recognition is one of the fascinating fields in the area of Computer science. Accuracy of speech recognition system may reduce due to the presence of noise present in speech signal. Therefore noise removal is an essential step in Automatic Speech Recognition (ASR) system and this paper proposes a new technique called combined thresholding for noise removal. Feature extraction is process of converting acoustic signal into most valuable set of parameters. This paper also concentrates on improving Mel Frequency Cepstral Coefficients (MFCC) features by introducing Discrete Wavelet Packet Transform (DWPT) in the place of Discrete Fourier Transformation (DFT) block to provide an efficient signal analysis. The feature vector is varied in size, for choosing the correct length of feature vector Self Organizing Map (SOM) is used. As a single classifier does not provide enough accuracy, so this research proposes an Ensemble Support Vector Machine (ESVM) classifier where the fixed length feature vector from SOM is given as input, termed as ESVM_SOM. The experimental results showed that the proposed methods provide better results than the existing methods.

3D simulation of interosseous interference in sagittal split ramus osteotomy for mandibular asymmetry

Santhiya Iswarya Vinothini Udayakumar,Dohyoung Kim,So-Young Choi,Tae-Geon Kwon 대한악안면성형재건외과학회 2023 Maxillofacial Plastic Reconstructive Surgery Vol.45 No.-

Background The purpose of this study was to evaluate the pattern of predicted interosseous interference and to determine the influencing factor to volume of bony interference using a computer-assisted simulation system. This retrospective study recruited 116 patients with mandibular prognathism who had undergone sagittal split ramus osteotomy (SSRO) with or without maxillary osteotomy. The patients were divided into 3 groups according to the amount of menton (Me) deviation: less than 2 mm (Group 1), 2–4 mm (Group 2), and more than 4 mm (Group 3). Changes in the distal segments following BSSRO and the volume of the interosseous interference between the proximal and distal segments were simulated after matching preoperative occlusion and postoperative expected occlusion with the cone-beam computed tomography data. Ramal inclinations and other skeletal measurements were analyzed before surgery, immediately after surgery, and at least 6 months after surgery. Results The anticipated interosseous interference was more frequently noted on the contralateral side of chin deviation (long side) than the deviated site (short side) in Groups 2 and 3. More interference volume was predicted at the long side (186 ± 343.9 mm3) rather than the short side (54.4 ± 124.4 mm3) in Group 3 (p = 0.033). The bilateral difference in the volume of the interosseous interference of the osteotomized mandible was significantly correlated with the Me deviation (r = − 0.257, p = 0.009) and bilateral ramal inclination (r = 0.361, p < 0.001). The predictor variable that affected the volume of the osseous interference at each side was the amount of Me deviation (p = 0.010). Conclusion By using the 3D simulation system, the potential site of bony collision could be visualized and successfully reduced intraoperatively. Since the osseous interference can be existed on any side, unilaterally or bilaterally, 3D surgical simulation is necessary before surgery to predict the osseous interference and improve the ramal inclination.

Orthognathic surgery for patients with fibrous dysplasia involved with dentition

Udayakumar, Santhiya Iswarya Vinothini,Paeng, Jun-Young,Choi, So-Young,Shin, Hong-In,Lee, Sung-Tak,Kwon, Tae-Geon Korean Association of Maxillofacial Plastic and Re 2018 Maxillofacial Plastic Reconstructive Surgery Vol.40 No.-

Background: Fibrous dysplasia (FD) is characterized by the replacement of normal bone by abnormal fibro-osseous connective tissue and typically treated with surgical contouring of the dysplastic bone. When dysplastic lesions involve occlusion, not only is surgical debulking needed, orthognathic surgery for correction of dentofacial deformity is mandatory. However, the long-term stability of osteotomized, dysplastic bone segments is a major concern because of insufficient screw-to-bone engagement during surgery and the risk of FD lesion re-growth. Case presentation: This case report reviewed two patients with non-syndromic FD that presented with maxillary occlusal canting and facial asymmetry. Le Fort I osteotomy with recontouring of the dysplastic zygomaticomaxillary region had been performed. The stability of osseous segments were favorable. However, dysplastic, newly formed bone covered the previous plate fixation site and mild bony expansion was observed, which did not influence the facial profile. Including the current cases, 15 cases of orthognathic surgery for FD with dentition have been reported in the literature. Conclusion: The results showed that osteotomy did not appear to significantly reduce the long-term stability of the initial fixation insufficiency of the screw to the dysplastic bone. However, based on our results and those of the others, long-term follow-up and monitoring are needed, even in cases where the osteotomized segment shows stable results.

Conversion of coconut waste into cost effective adsorbent for Cu(II) and Ni(II) removal from aqueous solutions

Abdul Rahman Abdul Rahim,Iswarya,Khairiraihanna Johari,Nasir Shehzad,Norasikin Saman,Hanapi Mat 대한환경공학회 2021 Environmental Engineering Research Vol.26 No.4

Desiccated coconut waste (DCW) is an agricultural waste that originates from the coconut milk processing industry. In this study, it was utilized for the removal of copper (Cu(II)) and nickel (Ni(II)) via adsorption process. The physicochemical characterization of the DCW adsorbent shows that the adsorbent have a surface area of 6.63 ㎡/g, have high elemental carbon content and existences of important functional groups on its surface. The adsorptive capability of DCW adsorbent in removing the heavy metal were conducted in batch studies. DCW adsorbent performed highest Ni(II) and Cu(II) adsorption capacity at pH 6, where equilibrium is achieved at 450 minutes. The kinetic analysis showed the adsorption agreed with pseudo-second order kinetic model, indicating the Cu(II) and Ni(II) adsorption were a chemical adsorption, limited by the film diffusion. The DCW adsorbent still retained its effective adsorption capacity after 2 adsorption-desorption cycles, which is one of the excellent criteria of a good adsorbent for an adsorption process.

Iron oxide nano-material: physicochemical traits and in vitro antibacterial propensity against multidrug resistant bacteria

Harshiny Muthukumar,Nivedhini Iswarya Chandrasekaran,Samsudeen Naina Mohammed,Saravanan Pichiah,Matheswaran Manickam 한국공업화학회 2017 Journal of Industrial and Engineering Chemistry Vol.45 No.-

The synthesis of Azadirachta indica leaf extract mediated Iron oxide nanoparticles (FeO-NPs) from ferricchloride were investigated. The characterization results confirmed that FeO-NPs were having goodphysicochemical traits. The FeO-NPs hold the resistance in ohmic range and coercivity value reached126emu/g. The FeO-Nps antioxidant efficiency was observed to be 95% of inhibition against 1, 1-diphenyl-2-picrylhydrazyl. The indigo-carmine dye decolourization of 79 and 85% under sunlight andUV-light irradiance were attained for FeO-NPs. The antibacterial and antibiofilm activities of FeO-NPsagainst bacterial pathogen were tested. The results confirmed that FeO-NPs have a virtuous propensityagainst gram negative than positive bacteria.