摘要 |
<p>PURPOSE: An apparatus and method for recognizing spell of voice and for mobile communications are provided to achieve a highly accurate recognition of individual monosyllabic letters, which when taken in aggregate to form a word, to produce even more accurate recognition. CONSTITUTION: An apparatus for a speech recognition system comprises a microphone(101), a front-end signal processor(102) for generating parametric representations of speech input signals, a pronunciation database(103), a letter similarity comparator(201) for comparing the parametric representation of the input signals with the parametric representations of letter pronunciations, and generating a sequence of associations between the input speech and the letters in the pronunciation database, a vocabulary database(203), a word similarity comparator(202) for comparing an aggregated plurality of the letters with the words in the vocabulary database and generating a sequence of associations between them, and a display(204) for displaying the selected letters and words for confirmation.</p> |