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 10 of 10 for “"Minimum classification error"”.

  1. A generalization of the minimum classification error (MCE) training method for speech recognition and detection

    … the Bayes decision theory usually assume uniform error cost and result in a ubiquitous use of the maximum a posteriori (MAP) decision policy and the paradigm of distribution estimation as practice in the design of a statistical pattern recognition system. The minimum classification error (MCE) …

    gatech Repository record for A generalization of the minimum classification error (MCE) training method for speech recognition and detection (opens in a new tab)

  2. Satellite Cloud Detection With Shortwave Channels: Algorithms, MISR Applications, and Three-Dimensional Radiative Effects

    … which has been known as the largest source of error in the retrievals of satellite geophysical products. This thesis consists of two parts: the operational part and the theoretical part. Specifically, the operational part is on the selection, implementation, and validation of the Radiometric …

    uiuc Repository record for Satellite Cloud Detection With Shortwave Channels: Algorithms, MISR Applications, and Three-Dimensional Radiative Effects (opens in a new tab)

  3. A statistical framework for the analysis of neural control of movement with aging and other clinical applications

    … of cepstral features significantly improved classification accuracy. Additionally, classification of young and elderly adults using Gaussian Mixture Models with Minimum Classification Error improved overall accuracy values. Contributions from the dissertation include demonstration of the …

    gatech Repository record for A statistical framework for the analysis of neural control of movement with aging and other clinical applications (opens in a new tab)

  4. Discriminative and adaptive training for robust speech recognition and understanding

    … are proposed for keyword spotting and topic classification: (1) To accurately recognize the semantically important keywords, the non-uniform error cost minimum classification error training of deep neural network (DNN) and bi-directional long short-term memory (BLSTM) acoustic models is …

    gatech Repository record for Discriminative and adaptive training for robust speech recognition and understanding (opens in a new tab)

  5. Towards robust conversational speech recognition and understanding

    … and understanding system. I. A non-uniform minimum classification error (MCE) approach is proposed which can achieve consistent and significant keyword spotting performance gains on both English and Mandarin large-scale spontaneous conversational speech tasks (Switchboard and HKUST Mandarin …

    gatech Repository record for Towards robust conversational speech recognition and understanding (opens in a new tab)

  6. Generalized multi-stream hidden Markov models.

    For complex classification systems, data is usually gathered from multiple sources of information that have varying degree of reliability. In fact, assuming that the different sources have the same relevance in describing all the data might lead to an erroneous behavior. The classification error …

    louisville Repository record for Generalized multi-stream hidden Markov models. (opens in a new tab)

  7. Objective-driven discriminative training and adaptation based on an MCE criterion for speech recognition and detection

    … MPE aim at direct minimization of the empirical error rate. As recent ASR applications become diverse, it has been increasingly recognized that realistic applications often require a model that can be optimized for a task-specific goal or a particular scenario beyond the general purposes of the …

    gatech Repository record for Objective-driven discriminative training and adaptation based on an MCE criterion for speech recognition and detection (opens in a new tab)

  8. Ensemble learning method for hidden markov models.

    For complex classification systems, data are gathered from various sources and potentially have different representations. Thus, data may have large intra-class variations. In fact, modeling each data class with a single model might lead to poor generalization. The classification error can be more …

    louisville Repository record for Ensemble learning method for hidden markov models. (opens in a new tab)

  9. Probabilistic modeling of neural data for analysis and synthesis of speech

    … multivariate Gaussians, using the method of minimum classification error for parameter estimation. Finally, we apply our joint waveforms and occurrence times spike-sorting method to neurological data in the context of a neural prosthesis for speech.

    gatech Repository record for Probabilistic modeling of neural data for analysis and synthesis of speech (opens in a new tab)

  10. Acoustic segment modeling and preference ranking for music information retrieval

    … approach is highly competitive on standard genre classification databases. Fundamental to the success of the acoustic segment modeling approach is the ability to model acoustical semantics in a musical piece, which is demonstrated by the detection of musical attributes on temporal characteristics. …

    gatech Repository record for Acoustic segment modeling and preference ranking for music information retrieval (opens in a new tab)