Abstract:
A system and method for providing a message-based communications infrastructure for automated call center post-call processing is described. Verbal speech utterances in a stream of recorded user messages are identified. The recorded user messages are parsed from a call with a user into a call center. The stream of recorded user messages are stored into a database maintained by the call center. The call is processed through an agent. One or more of the user messages is presented to the agent. Commands on the user messages are executed responsive to the agent.
Abstract:
A service server apparatus is provided which can easily cope with a correction of an error of a task performed based on the content of verbal speeches of a speaker. The service server apparatus includes a service activating unit that receives an instruction for performing a different task from a task performed by an application relating to a speech communication, a telephone/call control enabler that records verbal speeches of the speaker during a speech communication between a plurality of speech communication terminal device, a speech recognizing enabler which performs a task based on the recorded speeches and which generates task data including text data representing the result of the performance and speech data representing the result of the performance, a text translating enabler, and a speech synthesizing enabler. This service server apparatus provides the task data to at least either one of the plurality of speech communication terminal devices or another communication terminal device associated with the speech communication terminal device.
Abstract:
An automatic answering device and an automatic answering method for automatically answering to a user utterance are configured: to prepare a conversation scenario that is a set of input sentences and replay sentences, the input sentences each corresponding to a user utterance assumed to be uttered by a user, the reply sentences each being an automatic reply to the inputted sentence; to accept a user utterance; to determine the reply sentence to the accepted user utterance on the basis of the conversation scenario; and to present the determined reply sentence to the user. Data of the conversation scenario have a data structure that enables the inputted sentences and the reply sentences to be expressed in a state transition diagram in which each of the inputted sentences is defined as a morphism and the reply sentence corresponding to the inputted sentence is defined as an object.
Abstract:
In a system comprising a voice recognition module, a session manager, and a voice generator module, a method for providing a service to a user comprises receiving an utterance via the voice recognition module; converting the utterance into one or more structures using lexicon tied to an ontology; identifying concepts in the utterance using the structures; provided the utterance includes sufficient information, selecting a service based on the concepts; generating a text message based on the selected service; and converting the text message to a voice message using the voice generator.
Abstract:
The invention relates to a conferencing unit for multi-point communication in the course of a telephone conference. Previously, it was not possible to call up and document agreements and decisions in voice-based telephone conferences in a computer-aided manner. The reason was that in traditional conferencing units, all audio channels were mixed into an overall channel and therefore an undisturbed interaction of individual participants with the system is not possible. The invention enables an individual association of a conference participant with a decision processing unit, in which decisions can be announced in a dialog system and stored in a computer-readable format.
Abstract:
An automatic answering device and an automatic answering method for automatically answering to a user utterance are configured: to prepare a conversation scenario that is a set of input sentences and replay sentences, the input sentences each corresponding to a user utterance assumed to be uttered by a user, the reply sentences each being an automatic reply to the inputted sentence; to accept a user utterance; to determine the reply sentence to the accepted user utterance on the basis of the conversation scenario; and to present the determined reply sentence to the user. Data of the conversation scenario have a data structure that enables the inputted sentences and the reply sentences to be expressed in a state transition diagram in which each of the inputted sentences is defined as a morphism and the reply sentence corresponding to the inputted sentence is defined as an object.
Abstract:
A communication session is established between a mobile station and an interactive voice response system (figure 1). One or more menu options in a speech form are received at the mobile station. The mobile station converts these menu options from the speech form to a displayable form. A stored menu at the mobile station is updated with the displayable form. The updated menu may then be presented to the user. The menu options reflected in the displayable form may be stored in at the mobile station and/or at external devices that may or may not be associated with the IVR system.
Abstract:
A method and voice communicator to provide a voice communication is described. The method may include identifying text to be communicated and automatically processing the text to generate an audio equivalent of the text. For example, the text may be scraped from a web page. The method may include identifying an intended recipient of the audio equivalent and thereafter communicating the audio equivalent as a telephone communication (e.g., a voice mail message in a voice mailbox). Thus, identifying the intended recipient may include requesting a telephone number of a sender (caller) of the voice communication. In an embodiment, the method comprises monitoring selection by a user of a contact list available on the voice communicator wherein the contact list includes a plurality of recipient names and their associated telephone numbers. The audio equivalent is communicated to the recipient device over, for example, PSTN or VoIP network.
Abstract:
A system and method for providing a message-based communications infrastructure for automated call center post-call processing is described. Verbal speech utterances in a stream of recorded user messages are identified. The recorded user messages are parsed from a call with a user into a call center. The stream of recorded user messages are stored into a database maintained by the call center. The call is processed through an agent. One or more of the user messages is presented to the agent. Commands on the user messages are executed responsive to the agent.