Syllable-based Phonetic transcription by Maximum Likelihood Methods
نویسنده
چکیده
The transcription of orthographic words into phonetic symbols is one the principal steps of a text-to-speech system[l]. In such a system a suitable phonetic pronunciation must be supplied, without human intervention, for every word in the text. No dictionary, however large, will contain all words, let alone proper names, technical terms and other textual items commonly found in unrestricted texts. Consequently, an automatic transcription components is usually considered essential.
منابع مشابه
Automatic derivation of multiple variants of phonetic transcriptions from acoustic signals
This paper deals with two methods for automatically finding multiple phonetic transcriptions of words, given sample utterances of the words and an inventory of context-dependent subword units. The two approaches investigated are based on an analysis of theN -best phonetic decoding of the available utterances. In the set of transcriptions resulting from theN -best decoding of all the utterances,...
متن کاملFrom segmentation bootstrapping to transcription-to-word conversion
The mapping of a raw phonetic transcription to an orthographic word sequence is carried out in three steps: First, a syllable segmentation of the transcription is bootstrapped, based on unsupervised subtractive learning. Then, the syllables are grouped to word entities guided by non-linguistic distributional properties. Finally, the phonetic word segmentations are mapped onto entries of a canon...
متن کاملSyllable Based Transcription of English Words into Perso-Arabic Writing System
This paper presents a rule-based method for transcription of English words into the PersoArabic orthography. The method relies on the phonetic representation of English words such as the CMU pronunciation dictionary. Some of the challenging problems are the context-based vowel representation in the Perso-Arabic writing system and the mismatch between the syllabic structures of English and Persi...
متن کاملPhonetic transcription verification with generalized posterior probability
Accurate phonetic transcription is critical to high quality concatenation based text-to-speech synthesis. In this paper, we propose to use generalized syllable posterior probability (GSPP) as a statistical confidence measure to verify errors in phonetic transcriptions, such as reading errors, inadequate alternatives of pronunciations in the lexicon, letter-to-sound errors in transcribing out-of...
متن کاملMandarin Pronunciation Modeling Based on Cass Corpus1
The pronunciation variability is an important issue that must be faced with when developing practical automatic spontaneous speech recognition systems. In this paper, the factors that may affect the recognition performance are analyzed, including those specific to the Chinese language. By studying the INITIAL/FINAL (IF) characteristics of Chinese language and developing the Bayesian equation, w...
متن کامل