| 摘要 |
<p>Informational text is provided to a mobile terminal (104) capable of being coupled to a mobile communications network (102). Digitally-encoded voice data (218, 308) is received (902) at the mobile terminal (104) via the network (102). The digitally-encoded voice data (218, 308) is converted (904) to text (220, 312) via a speech recognition module (226, 318) of the mobile terminal (104). Informational portions (222, 314) of the text (220, 312) are identified (906) and made available (908) to an application (224, 232, 316) of the mobile terminal (104). In one configuration, speech recognition quality can be improved by extracting the informational text (530) from the near-end speech, and comparing to the text (522) obtained from the received voice data. In another configuration, an analog signal that originates from a public switched telephone network (610) is received (1002) at an element (600) of a mobile network (102). Speech recognition is performed (1004) on the analog signal to obtain text (618) that represents conversations contained in the analog signal. The analog signal is encoded (1006) to form digitally-encoded voice data (616) suitable for transmission to the mobile terminal (606, 620). The voice data (616) and the text (618) are then transmitted (1008) to the mobile terminal (606, 620).</p> |
