Abstract:
A dialog manager for a spoken dialog system includes a computer, a processor, and memory, comprising: a decision module for selecting a path from a plurality of alternative paths for a given call, wherein each path implements one of a plurality of strategies for a call flow; and a weighting module for weighting the path selection decision, wherein the weighting module is operatively connected to a probability estimator for estimating a probability value that a given path of the plurality of paths is the best performing path, wherein incoming calls are directed to each of the alternative paths selected by the decision module.
Abstract:
A method and system for operating a multitenancy telephony system including a call queue that stores call requests received from a plurality of users; an expandable and contractible telephony resource cluster that establishes call sessions for call requests; a analysis system that calculates capacity requirements of the system; a resource allocator that manages the scaling and operation of the telephony resource cluster; and a plurality of telephony network channels that are used as telephony communication channels for call sessions.
Abstract:
A system (30) and method for providing a multi-modal communications infrastructure for automated call center (11) operation is provided. A multi-modal call is accepted from a caller (12-15) through a telephony interface (35), which accommodates multi-modal calls including at least one of verbal speech and text messaging. Incoming speech in the multi-modal call is converted into transcribed text (57). Incoming text messaging is matched with the transcribed text (57). The multi-modal call is automatically assigned through a session manager (31) to a session under operation of a live agent (81). The transcribed text (57) and incoming text messaging are progressively processed during the session through an agent application (43) by performing a customer support scenario (22) interactively monitored and controlled by the live agent (81).
Abstract:
A method for accessing and browsing the internet through the use of a telephone and the associated DTMF signals is disclosed. The preferred embodiment provides a system that converts the information content of a web page from text to speech (voice signals), signals the hyperlink selections of a web page in an audio manner, and allows selection of the hyperlinks through the use of DTMF signals generated from a telephone keypad. Upon receiving a DTMF signal corresponding to a hyperlink, the corresponding web page is fetched and again delivered to the user via one of the available delivery methods such as voice, fax-on-demand, electronic mail, or regular mail.
Abstract:
An information guidance service system according to the present invention provides a user terminal (1) with information on a facility in use. The information guidance service system includes the user terminal (1) having a push-to-talk over cellular (PoC) function of performing a transceiver-mode communications; a PoC server (2) which controls the transceiver-mode communications with the PoC function to relay between the user terminal and an information guidance providing device (3); and the information guidance providing device (3) for providing the information on the facility in use to the user terminal (1). The information guidance providing device (3) includes a control circuit (31) that controls to communicate with the user terminal via the PoC server (2) and notify the user terminal of the information on the facility in use as a voice signal.
Abstract:
The application relates to audio caller identification. Audio caller identification relates to providing caller identification to the called party in spoken form via text-to-speech pronunciation of the calling party's name which is particularly important for visually-impaired users. However the conversion of the calling party's name from text form to a spoken form by a text-to-speech conversion often results in mispronunciation of the calling party's name. This problem is solved by the caller himself creates and edits a phonetic-alphabet representation of his name. The phonetic representation is conveyed to the called party as "caller-identification" information by messages that set up a call between the parties. The phonetic representation of the name is displayed to the second party, converted to speech, and/or converted to an alphabet of a language of the second party and then displayed to the second party.
Abstract:
A communication device (102) is described herein that is capable of enabling a user to select whether they want to use voice communications, text communications or voice/text communications to communicate with a remote communication device used by a person or an automated phone service. Also described herein are methods for making and using the communication device.
Abstract:
A system (10) and method (100) for providing a message-based communications infrastructure for automated call center operation is described. A call (54) from a user (12) into a call center (11) is accepted. The accepted call (54) includes a stream of transcribed verbal speech utterances (57). Each transcribed verbal speech utterance (57) is recorded as a user message (22). The accepted call (54) is assigned to a session (20), which is then assigned to an agent (81). The call (54) is progressively processed in the assigned session (20) by presenting each user message (22) to the assigned agent (81), executing commands responsive to the assigned agent (81), and sending an agent message (23) to the user (12). The agent message (23) includes a stream of synthesized audible speech utterances (63).