Supphanat Kanokphara

Learn More
Nowadays, the improvement of speech recognition technology is growing fast and many techniques are presented. However, even the best algorithm with carefully designed system cannot accomplish good performance speech recognition if the system is trained from poor corpus. Therefore, the speech corpus is the basic research that is necessary and should be(More)
Speech segmentations have been widely using in many speech applications. In speech synthesis, the quality of produced speech depends on the accuracy of labeled acoustic inventory. In speech recognition, segmented utterances according to the labels are usually used as a starting point for training speech models. The segmentation is often manually encoded(More)
Choice of the phonetic units speech recognizer is a factor greatly affecting the system performance. Phonetic units are normally defined according to the acoustic properties of a speech. Nevertheless, with the limit of training data, too delicate acoustic properties are ignored. Syllable structure is one of the properties usually ignored in English phonetic(More)
This paper proposes a work on phonetically balanced sentence (PB) and phonetically distributed sentence (PD) set, which are parts of the text prompt for speech recording in Large Vocabulary Continuous Speech Recognition (LVCSR) corpus for Thai language. Firstly, a protocol of Thai phonetic transcription and some essential rules of phonetic correction after(More)
Generally, a speech recognition system uses a fixed set of pronunciations according to the dictionary for training and decoding. However, even a well-defined lexicon cannot be used to support all variations in human’s pronunciation. Besides, in order to cover all possible pronunciations, the size of the dictionary would be too large to implement. Sharing(More)
The majority of speech recognition systems today commonly use Hidden Markov Models (HMMs) as acoustic models in systems since they can powerfully train and map a speech utterance into a sequence of units. Such systems perform even better if the units are context-dependent. Analogously, when HMM techniques are applied to the problem of articulatory feature(More)
HMMs are the dominating technique used in speech recognition today since they perform well in overall phone recognition. In this paper, we show the comparison of HMM methods and machine learning techniques, such as neural networks, decision trees and ensemble classifiers with boosting and bagging in the task of articulatory-acoustic feature classification.(More)
This paper is concerned with a novel methodology for generating phonetic questions used in tree-based state tying for speech recognition. In order to implement a speech recognition system, language-dependent knowledge which goes beyond annotated material is usually required. The approach presented here generates phonetic questions for decision trees are(More)
Last year National Electronics and Computer Technology (NECTEC) launched a speech corpus project for building a large-vocabulary speaker independent, continuous speechrecognition system. It is a cooperation project between NECTEC and universities with NECTEC as a host center. This paper gives details of the corpus including the sentence selection, the(More)