We report on an implemented grapheme to phoneme conversion architecture Given a set of examples spelling words with their associated phonetic represen tation in a language a grapheme to phoneme conversion system is automatically produced for that language which takes as its input the spelling of words and pro duces as its output the phonetic transcription according to the rules implicit in the ...

Connectionist learning of natural language words and their phonetic regularities is presented. The Neural Network (NN) model we employ in this problem is the Simple Recurrent Network, trained with the Backpropagation Through Time (BPTT) learning algorithm. During the training, it was assigned the task of predicting the next phoneme given one phoneme at each moment and keeping information of the...

Frequency counts are a measure of how much use a language makes of a linguistic unit, such as a phoneme or word. However, what is often important is not the units themselves, but the contrasts between them. A measure is therefore needed for how much use a language makes of a contrast, i.e. the functional load (FL) of the contrast. We generalize previous work in linguistics and speech recognitio...

Several factors affect the efficiency of bootstrapping approaches to the generation of pronunciation dictionaries. We focus on factors related to the underlying rule-extraction algorithms, and demonstrate variants of the Dynamically Expanding Context algorithm, which are beneficial for this application. In particular, we show that continuous updating of the learned rules, coupled with a new app...

One approach to the transcription of written text into sounds (phonetization) is to use a set of welldefined language-dependent rules, which are in most situations augmented by a dictionary of exceptional words that constitute their on rules. The process of transcribing into sounds starts by pre-processing the text into lexical items to which the rules are applicable. The rules can be segregate...

Imperfect and internal rhymes are two important features in rap music previously ignored in the music information retrieval literature. We developed a method of scoring potential rhymes using a probabilistic model based on phoneme frequencies in rap lyrics. We used this scoring scheme to automatically identify internal and line-final rhymes in song lyrics and demonstrated the performance of thi...

A talking head system (THS) is presented to animate the face of a speaking 3D avatar in such a way that it realistically pronounces the given Korean text. The proposed system consists of SAPI compliant text-to-speech (TTS) engine and MPEG-4 compliant face animation generator. The input to the THS is a unicode text that is to be spoken with synchronized lip shape. The TTS engine generates a phon...

Some applications of speech recognition, such as automatic directory information services, require very large vocabularies. In this paper, we focus on the task of recognizing surnames in an Interactive telephonebased Directory Assistance Services (IDAS) system, which supersedes other large vocabulary applications in terms of complexity and vocabulary size. We present a method for building compa...

Nonword pronunciation is a form of generalization behavior that has been at the center of debates about models of word recognition, the role of rules in explaining behavior, and the adequacy of the parallel distributed processing approach. An experiment yielded data concerning the pronunciation of a large corpus of nonwords. The data were then used to assess 2 models of naming: a model develope...

The phonotactic system is one of the interesting phonological systems to explain because it that regulates existence, abilities, and inability phoneme combinations a language. To end, this article describes Kaur language which includes (1) cluster (2) consonant series system. data in study were sourced from six key informants who domiciled Regency (Bengkulu Province) with criteria being between...