This paper gives an overview of current understanding of acoustic-phonetic issues arising when trying to recognize speech from non-native speakers. Regional accents can be modeled by systematic shifts in pronunciation. These can often better be represented by multiple models, than by pronunciation variants in the dictionary. The problem of non-native speech is much more difficult because it is ...

Detecting mispronunciations produced by non-native speakers and providing detailed instructive feedbacks are desired in computer assisted pronunciation training system (CAPT), as it is helpful to L2 learners to improve their pronunciation more effectively. In this paper, we present our preliminary study on detecting phonetic segmental mispronunciations on account of the erroneous articulation t...

In a recent work, we proposed an acoustic data-driven grapheme-to-phoneme (G2P) conversion approach, where the probabilistic relationship between graphemes and phonemes learned through acoustic data is used along with the orthographic transcription of words to infer the phoneme sequence. In this paper, we extend our studies to under-resourced lexicon development problem. More precisely, given a...

Automatically recognising children’s speech is a very difficult task. This difficulty can be attributed to the high variability in children’s speech, both within and across speakers. The variability is due to developmental changes in children’s anatomy, speech production skills et cetera, and manifests itself, for example, in fundamental and formant frequencies, the frequency of disfluencies, a...

Decoders that make use of token-passing restrict their search space by various types of token pruning. With use of the Language Model Look-Ahead (LMLA) technique it is possible to increase the number of tokens that can be pruned without loss of decoding precision. Unfortunately, for token passing decoders that use single static pronunciation prefix trees, full n-gram LMLA increases the needed n...

This study aims to identify the crucial prosodic factor for native speakers’ naturalness judgement of L2 pronunciation. Prosodic features are known to have more impact on the naturalness of L2 learners’ pronunciation than segmental features do. Among prosodic features, timing and pitch are looked at in this study as major prosodic factors which affect native speakers’ naturalness judgement of L...

In leading morpho-phonological theories and state-of-the-art text-to-speech systems it is assumed that word pronunciation cannot be learned or performed without in-between analyses at several abstraction levels (e.g., morphological, graphemic, phonemic, syllabic, and stress levels). We challenge this assumption for the case of English word pronunciation. Using igtree, an inductive-learning deci...

We introduce a novel method to diagnose pronunciation errors that are most critical to the intelligibility of L2 learners. A preliminary study showed that error rates computed by a speech recognition-based system can be used to characterize intelligibility. We deduce a probabilistic algorithm to derive intelligibility from error rates. We also define an error priority function that indicates wh...

We introduce a novel method to diagnose pronunciation errors that are most critical to the intelligibility of L2 learners. A prelimiary study showed that error rates computed by a speech recognition-based system can be used to characterize intelligibility. We deduce a probabilistic algorithm to derive intelligibility from error rates. We also define an error priority function that indicates whi...

We propose a sophisticated tying mechanism for modeling deletion transfonnations between dialects. We empirically show that the proposed tying mechanism reduces deletion errors by 33% when compared to a baseline system using a standard tying mechanism. Statistical tests show that the proposed and baseline models make statistically diOcrcnt errors, thus suggesting that they are complementary sys...