On this day in 2001, Lucent Technologies Inc. received a patent for a method of training a text-to-speech (TTS) system to assign intonational features — U.S. Patent No. 6,173,262.
Intonation can drastically change the meaning of a spoken phrase, which can obviously cause severe problems in TTS automation. For example, as provided in this patent, with respect to intonational phrasing, the sentence “The child isn’t screaming because he is sick” spoken as a single intonational phrase may lead the listener to infer that the child is, in fact, screaming, but not because he is sick. However, if the same sentence is spoken as two intonational phrases with an intonational phrase boundary between “screaming” and “because,” (i.e., “The child isn’t screaming, because he is sick”) the listener is likely to infer that the child is not screaming, and the reason is that he is sick.