AUTOMATED EXTRACTION OF SEMANTIC CONTENT AND GENERATION OF ASTRUCTURED DOCUMENT FROM SPEECH
摘要
<p num="1"><br/><br/><br/>Techniques are disclosed for automatically generating structured documents <br/>based on speech, including identification of relevant concepts and their <br/>interpretation. In one embodiment, a structured document generator uses an <br/>integrated process to generate a structured textual document (such as a <br/>structured textual medical report) based on a spoken audio stream. The spoken <br/>audio stream may be recognized using a language model which includes a <br/>plurality of sub-models arranged in a hierarchical structure. Each of the sub-<br/>models may correspond to a concept that is expected to appear in the spoken <br/>audio stream. Different portions of the spoken audio stream may be recognized <br/>using different sub-models. The resulting structured textual document may have <br/>a hierarchical structure that corresponds to the hierarchical structure of the <br/>language sub-models that were used to generate the structured textual document.<br/>