This paper presents two different tools which may be used as a support of speech recognition. The tool “transc” is the first one and it generates the phonetic transcription (pronunciation) of given utterance. It is based mainly on fixed rules which can be defined for Czech pronunciation but it can work also with specified list of exceptions which is defined on lexicon basis. It allows the usage...

In recent years, there are a considerable number of new immigrants in Taiwan. Although these people are in the good position to learn Chinese, the advantages are limited to speaking and listening. Recognizing Chinese characters is a tough task since one has to memorize the shape, meaning and pronunciation at the same time. Therefore, the cost of learning a single character is relatively high co...

In this paper, we focus on the modeling of coarticulation and pronunciation variation in Automatic Speech Recognition systems (ASR). Most ASR systems explicitly describe these production phenomena through context-dependent phoneme models and multiple pronunciation lexicons. Here, we explore the potential benefit of using feature spaces covering longer time segments in terms of implicit modeling...

In this paper, we describe a method for automatically generating a domain-dependent pronunciation lexicon using a data-driven approach. We also introduce an adaptation method to alleviate some of the errors caused by the data-driven rules which are derived from a relatively small volume of speech corpus. At first, pronunciation variation rules are extracted from a large volume of speech corpus ...

Regular English Pronunciation (REP) is an artificial accent of English designed to be more logically related to English spelling than modern naturally-occurring English accents. The REP pronunciation of words can be generated automatically with a set of just 200 rules and exceptions. These rules and exceptions have been measured to provide over 75% of standard pronunciations in running spoken E...

In this paper, a bi-lingual large vocaburary speech recognition experiment based on the idea of modeling pronunciation variations is described. The two languages under study are Mandarin Chinese and Taiwanese (Min-nan). These two languages are basically mutually unintelligible, and they have many words with the same Chinese characters and the same meanings, although they are pronounced differen...

Objective evaluation allows a model to be compared with other similar models. However, automatic pronunciation models should also be extensively evaluated by humans, since the ultimate goal of any pronunciation model is to produce an accurate pronunciation as judged by most people. This paper describes an initiative to evaluate and collect proper name pronunciations online, the development of t...

Multilinguality aspects are becoming increasingly important in the Automatic Speech Recognition (ASR) systems. It is apparent that coping with large variability of the speech signal is an even bigger challenge in multilingual ASR systems than it has been in conventional monolingual systems. In this paper, we address the importance of combining multilingual pronunciation modeling and acoustic mo...

This work presents a general development framework for automatic pronunciation assessment within computer-assisted language learning (CALL) together with several reenements of a previously described pronunciation scoring method. This method utilises a likelihood-based`Goodness of Pronunciation' (GOP) measure which in this work has been extended to include individual thresholds for each phone ba...

The pronunciation variations, which badly influenced the performance of ASR system, are serious in continuous speech, especially in spontaneous speech. Many research works are focused on pronunciation variation modeling in recent years. A framework for Chinese pronunciation variation modeling is described in this paper. The main idea is that the pronunciation variations are hidden in the recogn...