Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 6 of 6 for “"GMM classifier"”.

  1. Statistical Approaches for Signal Processing with Application to Automatic Singer Identification

    … we firstly study a traditional method, double GMM. Then an improved method, namely single GMM, is proposed. The experimental result shows that the detection accuracy of single GMM can be achieved as high as 96.42%. In terms of the background music removal, Non-negative Matrix Factorization …

    rit Repository record for Statistical Approaches for Signal Processing with Application to Automatic Singer Identification (opens in a new tab)

  2. A Soft Computing Based Approach for Multi-Accent Classification in IVR Systems

    … approaches are the Gaussian Mixture Model (GMM) and Hidden Markov Model (HMM). Of the two, GMM is the most widely implemented for accent classification. However, GMM performance depends on the initial partitions and number of Gaussian mixtures, both of which can reduce performance if poorly …

    waterloo Repository record for A Soft Computing Based Approach for Multi-Accent Classification in IVR Systems (opens in a new tab)

  3. Driver behavior classification and lateral control for automobile safety systems

    … classification method, Gaussian Mixture model (GMM), is applied to classify driver behavior. In this application, a low cost 1Hz GPS receiver is considered as the vehicle data acquisition equipment instead of other more costly sensors (such as steering angle sensor, throttle/brake position …

    njit Repository record for Driver behavior classification and lateral control for automobile safety systems (opens in a new tab)

  4. Autoregressive models for text independent speaker identification in noisy environments

    … It is reported that the Gaussian mixture model (GMM) classifier achieves very high classification accuracies (in the range 95% - 100%) when both the training and testing utterances are recorded in sound proof studio, i.e., there is neither additive noise nor spectral distortion to the speech …

    waterloo Repository record for Autoregressive models for text independent speaker identification in noisy environments (opens in a new tab)

  5. Automated segmentation and pathology detection in ophthalmic images

    … that are classified by a Gaussian Mixture Model (GMM) classifier. The proposed algorithm achieves more than 95% vessel segmentation accuracy on three publicly available data sets. Next, we present an iterative blood vessel segmentation algorithm that initially estimates the major blood vessels, …

    umn Repository record for Automated segmentation and pathology detection in ophthalmic images (opens in a new tab)

  6. Robust speaker recognition in the presence of speech coding distortion

    … are considered and use a Gaussian mixture model (GMM) classifier. The systems are trained on clean speech and tested on the decoded speech. To mitigate the performance loss due to mismatched training and testing conditions, four robust features, two enhancement approaches and feature (SI) and score …

    rowan Repository record for Robust speaker recognition in the presence of speech coding distortion (opens in a new tab)