Original Publication Date: 2003-Oct-25
Included in the Prior Art Database: 2003-Oct-25
Related PeopleOther Related People:
Today, multi-modal services providing not only speech-based telephony service but a broad variety of modalities, like pen input or visual and synthesized output, are available. If a telephone user wants to leave a message to a potential caller, it is advantageous to provide this message in a multi-modal form to cope with the different devices used for retrieving the left message. Here an automatic multi-modal answering machine is proposed, which allows leaving messages with different modalities to particular caller. Thus, apart from speech it is also capable of recording visual contents like web pages, SMS, MMS, or video streams. Depending on the calling device, the appropriate answer is generated and sent to the device. By allocating the incoming caller number to previously assigned messages, the answers can also be dedicated to particular caller or groups of caller. Furthermore, a multi-modal responder allows for processing multiple input modalities. For example stylus-written notes from a PDA (Personal Digital Assistant) can be provided as response content in form of a bitmap. The answer can then either be transmitted directly to an incoming caller, or the information that a MMS with the attached bitmap will be sent to him can be provided. Also, the management of the responder device itself can be performed multi-modal. Assignments of caller numbers, messages, or database entries can be made using speech, pen or keypad, according to the input device.