A Discriminative Segmental Speech Model and Its Application to Hungarian Number Recognition
نویسندگان
چکیده
Abstract. This paper presents a stochastic segmental speech recognizer that models the a posteriori probabilities directly. The main issues concerning the system are segmental phoneme classification, utterance-level aggregation and the pruning of the search space. For phoneme classification artificial neural networks and support vector machines are applied. Phonemic segmentation and utterance-level aggregation is performed with the aid of anti-phoneme modeling. At the phoneme level the system convincingly outperforms the HMM system trained on the same corpus, while at the word level it attains the performance of the HMM system trained without embedded training.
منابع مشابه
An Information-Theoretic Discussion of Convolutional Bottleneck Features for Robust Speech Recognition
Convolutional Neural Networks (CNNs) have been shown their performance in speech recognition systems for extracting features, and also acoustic modeling. In addition, CNNs have been used for robust speech recognition and competitive results have been reported. Convolutive Bottleneck Network (CBN) is a kind of CNNs which has a bottleneck layer among its fully connected layers. The bottleneck fea...
متن کاملEfficient Segmental Cascades for Speech Recognition
Discriminative segmental models offer a way to incorporate flexible feature functions into speech recognition. However, their appeal has been limited by their computational requirements, due to the large number of possible segments to consider. Multi-pass cascades of segmental models introduce features of increasing complexity in different passes, where in each pass a segmental model rescores l...
متن کاملSupport Vector Machines for Segmental Minimum Bayes Risk Decoding of Continuous Speech
Segmental Minimum Bayes Risk (SMBR) Decoding involves the refinement of the search space into sequences of small sets of confusable words. We describe the application of Support Vector Machines (SVMs) as discriminative models for the refined search spaces. We show that SVMs, which in their basic formulation are binary classifiers of fixed dimensional observations, can be used for continuous spe...
متن کاملTelephone Speech Recognition via the Combination of Knowledge Sources in a Segmental Speech Model
The currently dominant speech recognition methodology, Hidden Markov Modeling, treats speech as a stochastic random process with very simple mathematical properties. The simplistic assumptions of the model, and especially that of the independence of the observation vectors have been criticized by many in the literature, and alternative solutions have been proposed. One such alternative is segme...
متن کاملAssignment problem and its application in Nigerian institutions: Hungarian method approach
Assignment model is a powerful operations research techniques that can be used to solve assignment or allocation problem. This study applies the assignment model to the course allocation problem in Nigeria tertiary institution in order to maximize lecturers’ effectiveness. A well-structured questionnaire was used to obtain data from lecturers and solved with Hungarian method. The study revealed...
متن کامل