Modeling pronunciation variation is key for recognizing conversational speech. Previous efforts on pronunciation modeling by modifying dictionaries only yielded marginal improvement. Due to complex interaction between dictionaries and acoustic models, we believe a pronunciation modeling scheme is plausible only when closely coupled with the underlying acoustic model. This paper explores the use...

Modeling pronunciation variation is key for recognizing conversational speech. Rather than being limited to dictionary modeling, we argue that triphone clustering is an integral part of pronunciation modeling. We propose a new approach called enhanced tree clustering. This approach, in contrast to traditional decision tree based state tying, allows parameter sharing across phonemes. We show tha...

This paper examines the phenomenon of spelling pronunciation in Ghanaian English and shows that it has become one of the features of pronunciation that have diverged from „RP‟ (Received Pronunciation), the standard norm of English language proficiency that is taught to Ghanaians. The empirical investigation of spelling pronunciation was a selection of 50 words of English based on observation of...

The ultimate aim of the research reported on here is to develop an automatic testing system for Dutch pronunciation. In the experiment described in this paper automatic scores of telephone speech produced by native and non-native speakers of Dutch are compared with speci®c, i.e., temporal and segmental, and global pronunciation ratings assigned by three groups of experts: three phoneticians and...

PLASER is a multimedia tool with instant feedback designed to teach English pronunciation for high-school students of Hong Kong whose mother tongue is Cantonese Chinese. The objective is to teach correct pronunciation and not to assess a student’s overall pronunciation quality. Major challenges related to speech recognition technology include: allowance for non-native accent, reliable and corre...

Pronunciation of proper names that have different and varied language sources is an extremely hard task, even for humans. This thesis presents an attempt to improve automatic pronunciation of proper names by modeling the way humans do it, and tries to eliminate synthesis errors that humans would never make. It does so by taking into account the different language and language family sources and...

This paper presents different methods of handling pronunciation variations in Cantonese large-vocabulary continuous speech recognition. In an LVCSR system, three knowledge sources are involved: a pronunciation lexicon, acoustic models and language models. In addition, a decoding algorithm is used to search for the most likely word sequence. Pronunciation variation can be handled by explicitly m...

The context in which a phoneme occurs leads to consistent differences in how it is pronounced. Phonologists employ a variety of contextual descriptors, based on factors such as stress and syllable boundaries, to explain phonological variation. However, in developing pronunciation networks for speech recognition systems, little explicit use is made of context other than the use of whole word mod...

Generally, a speech recognition system uses a fixed set of pronunciations according to the dictionary for training and decoding. However, even a well-defined dictionary 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. This paper presents efficient strategies for ...

This paper reports on the early stages of a locally funded research and development project taking place at Rennes 2 university. It aims at developing a comprehensive pedagogical framework for pronunciation training for adult learners of English. This framework will combine a direct approach to pronunciation training (face-to-face teaching) with online instruction using and adapting existing Au...