Word embedding has made great achievements in many natural language processing tasks. However, the attempt to apply word embedding to the field of speech got few breakthroughs. The reason is that word vectors mainly contain semantic and syntactic information. Such high level features are difficult to be directly incorporated in speech related tasks compared to acoustic or phoneme related featur...

Tying of Hidden Markov Model states is an important issue for the use of triphones as modeling units in automatic speech recognition systems. This paper studies the application of a–priori rules for tying in combination with data driven methods. The baseline method features a combination of a–priori rules that reduce the theoretical number of units by an oder of magnitude and a simple back–off ...

This paper presents a distinctive phonetic features (DPFs) based phoneme recognition method by incorporating syllable language models (LMs). The method comprises three stages. The first stage extracts three DPF vectors of 15 dimensions each from local features (LFs) of an input speech signal using three multilayer neural networks (MLNs). The second stage incorporates an Inhibition/Enhancement (...

In this paper, we propose a segment-based non-parametric method of monophone recognition. We pre-segment the speech utterance into its underlying phonemes using a group-delay-based algorithm. Then, we apply the kNN/SASH phoneme classification technique to classify the hypothesized phonemes. Since phoneme boundaries are already known during the decoding, the search space is very limited and the ...

the paper analyses issues leading to errors in graphic object classifiers. thedistance measures suggested in literature and used as a basis in traditional, fuzzy, andneuro-fuzzy classifiers are found to be not suitable for classification of non-stylized orfuzzy objects in which the features of classes are much more difficult to recognize becauseof significant uncertainties in their location and...

To achieve high quality output speech synthesis systems, data-driven grapheme-to-phoneme (G2P) conversion is usually used to generate the phonetic transcription of out-of-vocabulary (OOV) words. To improve the performance of G2P conversion, this paper deals with the problem of conflicting phonemes, where an input grapheme can, in the same context, produce many possible output phonemes at the sa...

This study focuses on the effective pronunciation modelling of words from different languages encountered during the development of a Sepedi automatic speech recognition (ASR) system. While the speech corpus used for training the ASR system consists mostly of Sepedi utterances, many words from English (and other South African languages) are embedded within the Sepedi sentences. In order to mode...

In this work, we present an innovative approach for grapheme to phoneme conversion, which achieves very low error rates for languages like British English, American English and Dutch, and gives good generalization performances. One of the basic steps in the text-to-speech conversion performed by the speech synthesis systems is the phonetic transcription of the input text that can be considered ...

Effects of two phonics courses on Chinese L1 EFL beginner readers’ knowledge of the English alphabetic principle were compared. Two groups of children with matched baselines received aphonics course designed with the gist of either the existing phonics practice within Taiwan’s Primary English education (the EPP) or the Revelational Phonics Approach (the RPA). Fundamental differences set the two...

We present a novel data-driven language independent approach for grapheme to phoneme conversion, which achieves a phoneme error rate of 3.68% and a pronunciation error rate of 17.13% for English. We apply our stochastic model to the task of dictionary verification and conclude that it is able to detect spurious entries, which can then be examined and corrected by a human expert.