Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
6 results
Search Results
Item Repetition detection in stuttered speech(Springer Science and Business Media Deutschland GmbH info@springer-sbm.com, 2016) Ramteke, P.B.; Koolagudi, S.G.; Afroz, F.This paper mainly focuses on detection of repetitions in stuttered speech. The stuttered speech signal is divided into isolated units based on energy. Mel-frequency cepstrum coefficients (MFCCs), formants and shimmer are used as features for repetition recognition. These features are extracted from each isolated unit. Using Dynamic Time Warping (DTW) the features of each isolated unit are compared with those subsequent units within one second interval of speech. Based on the analysis of scores obtained from DTW a threshold is set, if the score is below the set threshold then the units are identified as repeated events. Twenty seven seconds of speech data used in this work, consists of 50 repetition events. The result shows that the combination of MFCCs, formants and shimmer can be used for the recognition of repetitions in stuttered speech. Out of 50 repetitions, 47 are correctly identified. © Springer India 2016.Item Advertisement detection in commercial radio channels(Institute of Electrical and Electronics Engineers Inc., 2016) Koolagudi, S.G.; Sridhar, S.; Elango, N.; Kumar, K.; Afroz, F.In this paper, real time identification of advertisement segments in a radio broadcast is performed. There are certain distinctive characteristics of advertisements that distinguish from the rest of the broadcasting information, Speech technology related to recognition of specific patterns in speech signal can characterize this distinction. Machine learning tools such as Hidden Markov Models, Artificial Neural Networks and Ensemble Method are used to classify advertisement and non-advertisement patterns. An ensemble classification technique gave a better classification performance. The system was created using blind audio segmentation for optimization of real time analysis. This work is done mainly using audio characteristics and can be extended to visual data. © 2015 IEEE.Item Layer based 3D clipping(Institute of Electrical and Electronics Engineers Inc., 2016) Kedia, Y.; Hendre, A.; Jain, S.; Afroz, F.; Koolagudi, S.G.In this paper, we propose an unconventional layer based clipping algorithm for 3D regions. In computer graphics, clipping is used to select the required part of a graphical object, cut it out from the object and display it separately. The proposed algorithm is not based on any other algorithm generally used for clipping in computer graphics and has a much better time efficiency than the other clipping algorithms available. The 3D space i.e. a cuboid is clipped w.r.t. a rectangular clipping window. The novelty of the algorithm is that 2D regions are being clipped down to the dimensions of the intersection region and then varied along the depth(z-axis) to get the volume of intersection. The algorithm has been implemented for both unrotated and rotated cuboids. The proposed algorithm can have massive applications in any field that requires layer-wise imaging of 3D spaces such as 3D printing, medical imaging, modelling, etc. given the simplicity of its implementation. © 2015 IEEE.Item Realistic golf flight simulation(Institute of Electrical and Electronics Engineers Inc., 2016) Sumukha, R.M.; Koolagudi, S.G.; Naresh, V.; Afroz, F.; Reddy, Y.N.A.The motion of the projectile is an easily observable phenomenon. The knowledge of the behavior of projectiles has been used extensively in warfare, since many centuries. From cannons to present day GPS-guided missiles, all rely on the principles of projectile motion. Apart from missiles, a flying golf ball is an interesting subject to study projectiles. The actual flight path can be simulated on a digital computer with computer graphics. In a natural setting, the golf ball's motion is dependent on various environmental factors. In this paper, apart from the initial velocity and angle of launch, resistance due to air and cross wind effects will also be considered. At the end of the projectile's flight, the landing will be simulated using bouncing ball physics. The theory for the object's motion will be utilized and then it will be adapted for simulation. The position and the configuration of the object and environmental conditions are taken as variables while modelling its flight. © 2016 IEEE.Item Optimization of Declarative Graphics by parallel programming(Institute of Electrical and Electronics Engineers Inc., 2017) Balachandran, M.; Nagori, K.; Rajan, A.; Koolagudi, S.G.; Afroz, F.Declarative Graphics is a new model built using the concepts of declarative programming in graphics. This paper presents an optimization of declarative graphics by parallelization. The optimization tries to reduce the backend processing of declarative graphics which induces an overhead. The parallelization is achieved by manipulating the inbuilt structure of declarative graphics. By parallelizing the backend computation a significant reduction in computation time has been achieved. © 2016 IEEE.Item Recognition and Classification of Pauses in Stuttered Speech Using Acoustic Features(Institute of Electrical and Electronics Engineers Inc., 2019) Afroz, F.; Koolagudi, G.K.Pauses plays an essential role in speech activities. Normally it helps the listener by creating a time and space to decode and interpret the message of a speaker. But in case of stuttering pauses disturbs the normal flow of speech. The uncontrolled, frequent and unplanned occurance of pasuses leads to slow speaking rate, results in broken words and increases the severity level of stuttering. Hence pauses and stuttering has a close relationship. Pauses are considered as one of the important pattern in diagnoisis and treatment of stuttering. In this work, an attempt has been made for the identification of inaudible (Silent or Unfilled) pauses from stuttered speech. The attributes like duration, frequency, position and distribution of pauses during speech tasks are measured and quantified. UCLASS stuttered speech corpus is considered for the analysis. Automatic blind segmentation approach is adopted to segment the speech signal into voice and unvoiced regions using dynamic threshold set based on energy and zero crossing rate (ZCR). 4 th formant frequencies are analysed to identify intra-morphic (unfilled) pauses present within voiced regions. The duratiion of intra-morphic pauses are analysed for stuttred speech and normal speech. It is observed that the duration of normal intra-morphic pause ranges from 150 ms-250 ms and inter-morphic pauses are <=250 ms and short pause have duration ranges from 50 ms-150 ms. Whereas in stuttering short intra-morphic pauses ranges from 10 ms to 50 ms, long pauses ranges from 250 ms to 1 or 2 seconds. Segmentation of the intra-morphic pauses is observed to acheive an accuracy of 98%. Results are compared and validated with manual method. © 2019 IEEE.