| 摘要 |
<p>Speech data are received by a a test system over telecommunications paths (10). Continuous speaker-independent speech recognition together with natural language recognition is used to reduce dynamic utterances to machine-encoded text (60) without requiring a prior training phase. Further, when configured by the end user to do so, the test system will convert common examples of dynamic speech, such as numbers, dates, times, and currency utterances, into their usual textual representation. This eliminates the limitation that all tested utterances need to be known by the test system in advance. The invention facilitates automated validation of data converted to text by allowing its input into an automated system (70) for independent access and validation of the data.</p> |
