In this paper, a developing voice-mail system is described which extracts keywords from continuously spoken mail. In this keyword extraction, a bottom-up approach to hypothesize the keywords and a top-down approach to verify them are integrated. First, a phoneme sequence is recognized in bottom-up mode, then keywords are hypothesized on the phoneme sequence. Finally, keyword candidates are veri...

Grapheme-to-phoneme (g2p) models are rarely available in low-resource languages, as the creation of training and evaluation data is expensive and time-consuming. We use Wiktionary to obtain more than 650k word-pronunciation pairs in more than 500 languages. We then develop phoneme and language distance metrics based on phonological and linguistic knowledge; applying those, we adapt g2p models f...

Digital technology has an increasing influence on writing processes. In this context, the question arises whether changes in mode (i.e., handwriting vs. computer-keyboard typing) also require assessments. However, data directly comparing influences children with and without developmental deficits are scarce. This study investigated of German-speaking, typically developing dyslexia (DD) from two...

Research into text-to-speech systems has become a rather important topic in the areas of linguistics and phonetics. Particularly for English, several text-to-speech systems have been established (cf. for' example llertz (1982), Klatt (1976)). For Dutch, text-to-speech systems are being developed at the University of Nijmegen (cf. Wester (1984)) and at the Universities of Utrecht and Leyden and ...

In speech technology it is very important to have a system capable of accurately performing grapheme-to-phoneme (G2P) conversion, which is not an easy task especially if talking about languages like English where there is no obvious letter-phone correspondence. Manual rules so widely used before are now leaving the way open for the machine learning techniques and language independent tools. In ...

Grapheme-to-phoneme (G2P) conversion is a very important component in a Text-to-Speech (TTS) system. Determining the pronunciation of polyphone characters is the main problem that the G2P component in a Mandarin TTS system faces. By studying the distribution of polyphones and their characteristics in a large text corpus with corrected pinyin transcriptions, this paper points out that correct G2...

In speech technology it is very important to have a system capable of accurately performing grapheme-to-phoneme (G2P) conversion, which is not an easy task especially if talking about languages like English where there is no obvious letter-phone correspondence. Manual rules so widely used before are now leaving the way open for the machine learning techniques and language independent tools. In ...