A statistical model for predicting pronunciation
نویسنده
چکیده
A general statistical model for the prediction of pronunciation given the orthographic transcript or the canonical pronunciation of a spoken utterance is described. The model is based on a Markov process that can be derived from a set of statistically weighted re-write rules. The automatic learning of such re-write rules based on annotated speech data is illustrated. One possible application of the pronunciation model is the automatic phonetic segmentation and labelling of speech by augmenting the Markov process with Hidden Markov Models for phonetic segments. A publicly accessible system using the model for the automatic phonetic segmentation and labelling of 14 different languages is presented.
منابع مشابه
Japanese Pronunciation Prediction as Phrasal Statistical Machine Translation
This paper addresses the problem of predicting the pronunciation of Japanese text. The difficulty of this task lies in the high degree of ambiguity in the pronunciation of Japanese characters and words. Previous approaches have either considered the task as a word-level classification problem based on a dictionary, which does not fare well in handling out-of-vocabulary (OOV) words; or solely fo...
متن کاملPredicting Word Pronunciation in Japanese
This paper addresses the problem of predicting the pronunciation of Japanese words, especially those that are newly created and therefore not in the dictionary. This is an important task for many applications including text-to-speech and text input method, and is also challenging, because Japanese kanji (ideographic) characters typically have multiple possible pronunciations. We approach this p...
متن کاملStatistical Modeling of Pronunciation Variation by Hierarchical Grouping Rule Inference
In this paper, a data-driven approach to statistical modeling pronunciation variation is proposed. It consists of learning stochastic pronunciation rules. The proposed method jointly models different rules that define the same transformation. Hierarchic Grouping Rule Inference (HIEGRI) algorithm is proposed to generate this model based on graphs. HIEGRI algorithm detects the common patterns of ...
متن کاملStochastic Pronunciation Modelling for Out-of-Vocabulary Spoken Term Detection
Spoken term detection (STD) is the name given to the task of searching large amounts of audio for occurrences of spoken terms, which are typically single words or short phrases. One reason that STD is a hard task is that search terms tend to contain a disproportionate number of out-of-vocabulary (OOV) words. The most common approach to STD uses subword units. This, in conjunction with some meth...
متن کاملThe Impact of Computer–Assisted Language Learning (CALL) /Web-Based Instruction on Improving EFL Learners’ Pronunciation Ability
The purpose of this study was to investigate the effect of CALL/Web-based instruction on improving EFL learners’ pronunciation ability. To this end, 85 students who were enrolled in a language institute in Rasht were selected as subjects. These students were given the Oxford Placement Test in order to validate their proficiency levels. They were then divided into two groups of 30 and were...
متن کامل