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 20 of 29 for “"Discriminative training"”.
-
GEOMETRIC APPROACHES TO DISCRIMINATIVE TRAINING
Discriminative training as a general machine learning approach has wide applications in tasks like Natural Language Processing (NLP) and Automatic Speech Recognition (ASR). In this thesis, we are interested in online methods for discriminative training due to their simplicity, efficiency and …
-
Towards Efficient and Robust Automatic Speech Recognition: Decoding Techniques and Discriminative Training
… two aspects of speech recognition, decoding and training of acoustic models, to improve speech recognition performance in different conditions. A major part of this thesis studies discriminative training of acoustic models. The emphasis is on the most popular algorithm for discriminative model …
-
Objective-driven discriminative training and adaptation based on an MCE criterion for speech recognition and detection
… speech recognition systems is commonly based on discriminative criteria. Different from the paradigm of the conventional distribution estimation such as maximum a posteriori (MAP) and maximum likelihood (ML), the most popular discriminative criteria such as MCE and MPE aim at direct minimization …
-
Training Machine Translation for Human Acceptability
Discriminative training, a.k.a. tuning, is an important part of Statistical Machine Translation. This step optimises weights for the several statistical models and heuristics used in a machine translation system, in order to balance their relative effect on the translation output. Different weights …
-
The functional properties of a conditioned cue
… Experiment I studied the question whether discriminative training was necessary for establishing an effective secondary motivator. Two groups of rats experienced differential food-buzzer exposure on Days 1-3 of the experiment. For one group, food and buzzer were always paired; this pairing …
-
Soft margin estimation for automatic speech recognition
In this study, a new discriminative learning framework, called soft margin estimation (SME), is proposed for estimating the parameters of continuous density hidden Markov models (HMMs). The proposed method makes direct use of the successful ideas of margin in support vector machines to improve …
-
Improved Online Learning and Modeling for Feature-Rich Discriminative Machine Translation
… systems learn how to translate by constructing a discriminative model based on statistics from the data. A growing number of methods for discriminative training have been proposed, but most suffer from limitations hindering their utility for training feature-rich models on large amounts of data. …
-
Bidirectional Learning in Recurrent Neural Networks Using Equilibrium Propagation
… equilibrium propagation has only been applied to discriminative categorization tasks. This thesis generalizes equilibrium propagation to bidirectional learning with asymmetric weights. Simultaneously learning the discriminative as well as generative transformations for a set of data points and …
-
Speaker Representation Learning under Self-supervised and Knowledge Transfer Setting
… while the second integrates clustering and discriminative training. This framework is further streamlined by introducing the self-supervised reflective learning approach, central to which is self-supervised knowledge distillation, optimized to mitigate label noise effects. This approach …
-
Temporally Varying Weight Regression for Speech Recognition
… for acoustic modelling due to its efficient training and decoding. HMM state output probability of an observation is assumed to be independent of the other states and the surrounding observations. Since temporal correlation between observations exists due to the nature of speech, this …
-
Probabilistic Graphical Models and Algorithms for
… (CRFs). Here, I present a new semi-supervised training procedure for CRFs that can be used to train sequence segmentors and labellers from a combination of labeled and unlabeled training data. Such learning algorithms can be applied to protein and gene name entity recognition problems. This …
-
Ensemble acoustic modeling in automatic speech recognition
… of several successful techniques of single model training in speech recognition on the proposed ensemble acoustic models, including Cross Validation Expectation Maximization (CVEM), Discriminative Training (DT), and Multiple Layer Perceptron (MLP) features. We have evaluated the proposed methods …
-
Gradient Based Mrf Learning For Image Restoration And Segmentation
… The research presented will describe a new discriminative training algorithm and its implementation. The MRF model will be trained by optimizing its parameters so that the minimum energy solution of the model is as similar as possible to the ground-truth. While previous work has relied on …
-
Gaussian Mixture Models and Neural Networks for Automatic Speaker Identification
… combination of maximum likelihood and discriminative training, using both GMMs and NNs should give a better recognition rate than either method alone. Thus, fusion approaches to combine the Gaussian Mixture Models and neural networks for Speaker ID are proposed and tested for various …
-
Discriminative and adaptive training for robust speech recognition and understanding
… of deep learning. To achieve robust ASU, two discriminative training objectives 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 …
-
Towards robust conversational speech recognition and understanding
… front-end preprocessing, speaker adaptive training or multiple decoding passes. III. To study the specific case of conversational speech recognition in the presence of competing talkers, several multi-style training setups of DNNs are investigated and a joint decoder operating on …
-
Bernoulli HMMs for Handwritten Text Recognition
… On the other hand, this guarantees that no discriminative information is filtered out during feature extraction (most HTR available datasets can be easily binarized without a relevant loss of information). In this thesis, all the HMM theory required to develop a HMM based HTR toolkit is …
-
Generalized multi-stream hidden Markov models.
… the minimum classification error (MCE) discriminative training algorithm to include stream relevance weights. For the continuous HMM, we introduce a. new approach that integrates the stream relevance weights in the objective function. Our approach is based on the linearization of the …
-
An ensemble speaker and speaking environment modeling approach to robust speech recognition
… the environment space; then, we propose a discriminative training algorithm to enhance discrimination across environment super-vectors and therefore broaden the coverage of the ensemble environment space. For the online phase, we study methods to increase the efficiency and precision in …
-
Advances in unlimited-vocabulary speech recognition for morphologically rich languages
… for morphologically rich languages. Before training the statistical n-gram language models on a large text corpus, the words in the corpus are automatically segmented into smaller fragments, referred to as morphs. The morphs are then used as modelling units of the n-gram models instead of …
Page 1 of 2