Improving letter-to-pronunciation accuracy with automatic morphologically-based stress prediction
نویسنده
چکیده
Robust text-to-speech (TTS) systems require a letter-topronunciation module for generating the pronunciations of words missing from the system lexicon. These pronunciations must specify not only the phone sequence that corresponds to an input orthography, but also the location of lexical stress. However, letter-to-pronunciation modules that make use of a window of context letters around a target letter normally cannot “see” larger-context morphological information that is highly correlated with stress location. The present work demonstrates that by adding a new component that uses morphological information to predict which letter of a word might receive primary stress, and then using the resulting “stressed letters” as input to a decision tree stressed-letter-topronunciation component, improvements to both stress accuracy and phone accuracy are obtained in American English, British English, and German. Furthermore, using stressed letters as the input to the decision tree also improves phone accuracy when stress is not required in the output pronunciation, as is conventionally the case for automatic speech recognition (ASR).
منابع مشابه
Computer Assisted Pronunciation Teaching (CAPT) and Pedagogy: Improving EFL learners’ Pronunciation Using Clear Pronunciation 2 Software
This study examined the impact of Clear Pronunciation 2 software on teaching English suprasegmental features, focusing on stress, rhythm and intonation. In particular, the software covers five topics in relation to suprasegmental features including consonant cluster, word stress, connected speech, sentence stress and intonation. Seven Iranian EFL learners participated in this study. The study l...
متن کاملImproving the accuracy of pronunciation p
This paper describes a technique which improves the accuracy of pronunciation prediction for unit selection TTS. It does this by performing an orthography-based context-dependent lookup on the unit database. During synthesis, the pronunciations of words which have matching contexts in the unit database are determined. Pronunciations not found using this method are determined using traditional l...
متن کاملLetter to sound rules for accented lexicon compression
This paper presents trainable methods for generating letter to sound rules from a given lexicon for use in pronouncing out-ofvocabulary words and as a method for lexicon compression. As the relationship between a string of letters and a string of phonemes representing its pronunciation for many languages is not trivial, we discuss two alignment procedures, one fully automatic and one hand seede...
متن کاملTreetalk-d: a Machine Learning Approach to Dutch Word Pronunciation
We present experimental results concerning the application of the IGTree decision-tree learning algorithm to Dutch word pronunciation. We evaluate four diierent Dutch word pronunciation systems conngured to test the utility of modularization of grapheme{to{phoneme transcription (G) and stress prediction (S). Both training and testing data are extracted from the CELEX II lexical database. Experi...
متن کاملImproving Pronunciation Accuracy of Proper Names with Language Origin Classes
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...
متن کامل