This paper describes the implementation of a full-scale pronunciation lexicon for Turkish based on a two-level morphological analyzer. The system produces at its output, a parallel representation of the pronunciation and the morphological analysis of the word form so that morphological disambiguation can be used to disambiguate pronunciation when necessary. The pronunciation representation is b...

The accurate phonetic transcription is very important for different fields of speech technologies. In speech synthesis, it is the benchmark for the voice segmentation, and therefore one of the crucial points for the synthesized speech pronunciation quality. In ASR the availability of matching phonetic transcription allows a higher recognition precision. Use of different dictionaries could impro...

This thesis reports the investigations into the task of phone-level pronunciation error detection, the performance of which is heavily affected by the imbalanced distribution of the classes in a manually annotated data set of non-native English (Read Aloud responses from the TOEFL Junior Pilot assessment). In order to address problems caused by this extreme class imbalance, two machine learning...

There are seven cases of grapheme to phoneme in a text to speech system (Yarowsky, 1997). Among them, the most difficult task is disambiguating the homograph word, which has the same POS but different pronunciation. In this case, different pronunciations of the same word always correspond to different word senses. Once the word senses are disambiguated, the problem of GTP is resolved. There is ...

speech learning changes over the life span and to explain why "earlier is better" as far as learning to pronounce a second language (L2) is concerned. An assumption we make is that the phonetic systems used in the production and perception of vowels and consonants remain adaptive over the life span, and that phonetic systems reorganize in response to sounds encountered in an L2 through the addi...

Many learning tasks require substantial skills training. Ideally, the student might benefit the most from having a human expert – a teacher or trainer – at hand throughout, but human expertise remains a scarce resource. The second-best solution could be to do skills training with a computer-based self-training system. This vision of the computer as tutor currently motivates increasing efforts w...

We propose a method for modeling pronunciation variation in the context of spell checking for non-native writers of English. Spell checkers, typically developed for native speakers, fail to address many of the types of spelling errors peculiar to non-native speakers, especially those errors influenced by differences in phonology. Our model of pronunciation variation is used to extend a pronounc...

Recent research has shown that a properly designed ASRbased CALL system (Dutch-CAPT) was capable of detecting pronunciation errors and of providing comprehensible feedback on pronunciation. Since pronunciation is not the only skill required for speaking a second language, we explored the possibility of extending the Dutch-CAPT approach to other aspects of speaking proficiency like morphology an...