Conference Papers

Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506

Browse

Author: search.filters.author.Gopalakrishnan, A.

Search Results

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Optic disc segmentation using circular hough transform and curve fitting
    (Institute of Electrical and Electronics Engineers Inc., 2015) Gopalakrishnan, A.; Almazroa, A.; Raahemifar, K.; Lakshminarayanan, V.
    We present a technique to segment the optic disc (OD) boundary from a color retinal fundus image. The technique used involves the extraction and removal of blood vessels using a top hat transform and an inpainting process. Then, a circular Hough transform is applied to the detected edges to obtain a coarse boundary of the OD and following which probable points of the optic disc are fed to a curve fitting algorithm which uses a higher order polynomial to draw the final boundary of the optic disc. The optic disc segmentation is a crucial part in estimating the CDR (Cup-to-disc ratio) which can be used as an early indicator of glaucoma and for following the progression/remission of the disease. © 2015 IEEE.
  • No Thumbnail Available
    Item
    Feature selection and model optimization for semi-supervised speaker spotting
    (European Signal Processing Conference, EUSIPCO, 2016) Chetupalli, S.R.; Gopalakrishnan, A.; Sreenivas, T.V.
    We explore, experimentally, feature selection and optimization of stochastic model parameters for the problem of speaker spotting. Based on an initially identified segment of speech of a speaker, an iterative model refinement method is developed along with a latent variable mixture model so that segments of the same speaker are identified in a long speech record. It is found that a GMM with moderate number of mixtures is better suited for the task than a large number mixture model as used in speaker identification. Similarly, a PCA based low-dimensional projection of MFCC based feature vector provides better performance. We show that about 6 seconds of initially identified speaker data is sufficient to achieve > 90% performance of speaker segment identification. © 2016 IEEE.
  • No Thumbnail Available
    Item
    Comparison of low-dimension speech segment embeddings: Application to speaker diarization
    (Institute of Electrical and Electronics Engineers Inc., 2019) Chetupalli, S.R.; Sreenivas, T.V.; Gopalakrishnan, A.
    Segment clustering is a crucial step in unsupervised speaker diarization. Bottom-up approaches, such as, hierarchical agglomerative clustering technique are used traditionally for segment clustering. In this paper, we consider the top-down approach to clustering, in which a speaker sensitive, low-dimensional representation of segments (speaker space) is obtained first, followed by Gaussian mixture model (GMM) based clustering. We explore three methods of obtaining the low dimension segment representation: (i) multi-dimensional scaling (MDS) based on segment to segment stochastic distances; (ii) traditional principal component analysis (PCA), and (iii) factor analysis (i-vectors), of GMM mean super-vectors. We found that, MDS based embeddings result in better representation and hence result in better diarization performance compared to PCA and even i-vector embeddings. © 2019 IEEE.