摘要 |
The present invention relates to a speech recognition method and a speech recognition apparatus for selecting, via speech input, an item from a list of items. A speech recognition apparatus for selecting, via a speech input (6), an item from a list (10) of items, comprises a subword unit speech recognition means (1) for recognizing a string of subword units for the speech input (6); a subword unit comparing means (2) for comparing the recognized string of subword units with subword unit transcriptions of the list items and for generating a candidate list (11) of the best matching items based on the comparison results; and a second speech recognition means (3) for recognizing and selecting an item from the candidate list (11), which best matches the speech input (6). At least two subword unit speech recognition means (1) are provided, each subword unit speech recognition means (1) being configured to recognize subword units of a different language. The subword unit comparing means (2) is configured to compare the strings of subword units recognized by the at least two subword unit speech recognition means (1) with the subword unit transcriptions of the list items and to insert the best matching items in the candidate list (11).
|