Abstract: Systems, methods, and programs, for evaluating audio messages store a model that may include language patterns, audio patterns, and/or metafeatures that indicate a likelihood that the audio message is a spam message or a non-spam message and compare the content of the input audio message with the model. Based on the comparison, the systems, methods, and programs identify the input audio message as a spam message or a non-spam message.

Abstract: A method of generating a natural language model for use in a spoken dialog system is disclosed. The method comprises using sample utterances and creating a number of hand crafted rules for each call-type defined in a labeling guide. A first NLU model is generated and tested using the hand crafted rules and sample utterances. A second NLU model is built using the sample utterances as new training data and using the hand crafted rules. The second NLU model is tested for performance using a first batch of labeled data. A series of NLU models are built by adding a previous batch of labeled data to training data and using a new batch of labeling data as test data to generate the series of NLU models with training data that increases constantly. If not all the labeling data is received, the method comprises repeating the step of building a series of NLU models until all labeling data is received.

Abstract: A voice-enabled help desk service is disclosed. The service comprises an automatic speech recognition module for recognizing speech from a user, a spoken language understanding module for understanding the output from the automatic speech recognition module, a dialog management module for generating a response to speech from the user, a natural voices text-to-speech synthesis module for synthesizing speech to generate the response to the user, and a frequently asked questions module. The frequently asked questions module handles frequently asked questions from the user by changing voices and providing predetermined prompts to answer the frequently asked question.

Abstract: A method is disclosed for generating labeled utterances from human-human utterances for use in training a semantic classification model for a spoken dialog system. The method comprises augmenting received human-human utterances with data that relates to call-type gaps in the human-human utterances, augmenting the received human-human utterances by placing at least one word in the human-human utterances that improves the training ability of the utterances according to the conversation patterns of the spoken dialog system, clausifying the human-human utterances, labeling the clausified and augmented human-human utterances and building the semantic classification model for the spoken dialog system using the labeled utterances.

Abstract: A system and method to provide content and call attributes for a destination phone number using a click-to-dial connection includes accepting a query, retrieving links to a document, and searching through cached data using the query to identify relevant or destination number information. If no match is found, the method continues with accessing the document identified by the link for identifying relevant number information and creating a click-to-dial icon to link to the relevant numbers included in the relevant phone number information identified by the query. Next, a popup box for content relevant to the click-to-dial icon and a click feature on the popup box are created to retrieve call destination attributes for viewing by a user. Further, computer instructions create at least one communication connection between two communication devices after viewing call destination attributes.

Abstract: A system and method to provide content and call attributes for a destination phone number using a click-to-dial connection includes accepting a query, retrieving links to a document, and searching through cached data using the query to identify relevant or destination number information. If no match is found, the method continues with accessing the document identified by the link for identifying relevant number information and creating a click-to-dial icon to link to the relevant numbers included in the relevant phone number information identified by the query. Next, a popup box for content relevant to the click-to-dial icon and a click feature on the popup box are created to retrieve call destination attributes for viewing by a user. Further, computer instructions create at least one communication connection between two communication devices after viewing call destination attributes.

Abstract: A method is disclosed for designing a labeling guide for use by a labeler in labeling data used for training a spoken language understanding (SLU) module for an application. The method comprises a labeling guide designer selecting domain-independent actions applicable to an application, selecting domain-dependent objects according to characteristics of the application, and generating a labeling guide using the selected domain-independent actions and selected domain-dependent objects. An advantage of the labeling guide generated in this manner is that the labeling guide designer can easily port the labeling guide to a new application by selecting a set of domain-independent action and then selecting the domain-dependent objects related to the new application.

Abstract: A method of generating a natural language model for use in a spoken dialog system is disclosed. The method comprises using sample utterances and creating a number of hand crafted rules for each call-type defined in a labeling guide. A first NLU model is generated and tested using the hand crafted rules and sample utterances. A second NLU model is built using the sample utterances as new training data and using the hand crafted rules. The second NLU model is tested for performance using a first batch of labeled data. A series of NLU models are built by adding a previous batch of labeled data to training data and using a new batch of labeling data as test data to generate the series of NLU models with training data that increases constantly. If not all the labeling data is received, the method comprises repeating the step of building a series of NLU models until all labeling data is received.

Abstract: A method of generating a natural language model for use in a spoken dialog system is disclosed. The method comprises using sample utterances and creating a number of hand crafted rules for each call-type defined in a labeling guide. A first NLU model is generated and tested using the hand crafted rules and sample utterances. A second NLU model is built using the sample utterances as new training data and using the hand crafted rules. The second NLU model is tested for performance using a first batch of labeled data. A series of NLU models are built by adding a previous batch of labeled data to training data and using a new batch of labeling data as test data to generate the series of NLU models with training data that increases constantly. If not all the labeling data is received, the method comprises repeating the step of building a series of NLU models until all labeling data is received.

Abstract: A voice-enabled help desk service is disclosed. The service comprises an automatic speech recognition module for recognizing speech from a user, a spoken language understanding module for understanding the output from the automatic speech recognition module, a dialog management module for generating a response to speech from the user, a natural voices text-to-speech synthesis module for synthesizing speech to generate the response to the user, and a frequently asked questions module. The frequently asked questions module handles frequently asked questions from the user by changing voices and providing predetermined prompts to answer the frequently asked question.

Abstract: A voice-enabled help desk service is disclosed. The service comprises an automatic speech recognition module for recognizing speech from a user, a spoken language understanding module for understanding the output from the automatic speech recognition module, a dialog management module for generating a response to speech from the user, a natural voices text-to-speech synthesis module for synthesizing speech to generate the response to the user, and a frequently asked questions module. The frequently asked questions module handles frequently asked questions from the user by changing voices and providing predetermined prompts to answer the frequently asked question.

Abstract: A computerized method is disclosed for presenting advertising data extracted from a video data stream, the method including storing a plurality of advertising data items extracted from the video data stream at an end user device; and displaying a plurality of sorted advertising indicator data items at the end user device, wherein each of the advertising indicator data items indicates one of the plurality of stored advertising data items. A system is disclosed for performing the method. A data structure is disclosed providing a functional and structural interrelationship between a processor in the system and data in the data structure.

Abstract: A method is disclosed for designing a labeling guide for use by a labeler in labeling data used for training a spoken language understanding (SLU) module for an application. The method comprises a labeling guide designer selecting domain-independent actions applicable to an application, selecting domain-dependent objects according to characteristics of the application, and generating a labeling guide using the selected domain-independent actions and selected domain-dependent objects. An advantage of the labeling guide generated in this manner is that the labeling guide designer can easily port the labeling guide to a new application by selecting a set of domain-independent action and then selecting the domain-dependent objects related to the new application.

Abstract: A system for understanding entries, such as speech, develops a classifier by employing prior knowledge with which a given corpus of training entries is enlarged threefold. A rule is created for each of the labels employed in the classifier, and the created rules are applied to the given corpus to create a corpus of attachments by appending a weight of ?p(x), or 1??p(x), to labels of entries that meet, or fail to meet, respectively, conditions of the labels' rules, and to also create a corpus of non-attachments by appending a weight of 1??p(x), or ?p(x), to labels of entries that meet, or fail to meet conditions of the labels' rules.

Abstract: Method and apparatus for invoking multimodal interaction in a VOIP call is described. In one example, handling a call at a first client device in a packet network is described. The first client device obtains device capabilities of a second client device in response to the call. The device capabilities are processed to determine whether the second client device is capable of graphical display or graphical interaction. If so, the first client device follows a multimodal call flow. Otherwise, the first client device follows a voice-only call flow.

Abstract: A method and apparatus for providing a click-to-talk service for advertisements carried over packet networks such as digital cable networks, Voice over Internet Protocol (VoIP) and Service over Internet Protocol (SoIP) networks are disclosed. For example, an enterprise customer subscribes to a service with a service provider that provides a click-to-talk feature with its advertisements on television channels. In one embodiment, the network service provider obtains meta-information from a video content and transmits the meta-information and the video content to a set-top box. The network service provider also enables consumers while viewing the advertisements to click on their remote control to initiate a call to talk to the advertising enterprise entity. Thus, when the consumer clicks-to-talk to the enterprise entity, the network service provider enables the consumer to reach the enterprise entity immediately.

Abstract: Method and apparatus for maintaining state information on a client device configured for voice-over-internet protocol (VOIP) communication is described. In one example, a VOIP call between the client device and an endpoint device through a packet network is established. State information is sent from the client device to the endpoint device during the VOIP call. The state object having the state information embedded therein is received from the endpoint device at the client device. The state object is stored in the client device. The state object may be retrieved from the client device during the VOIP call or a subsequent VOIP call in response to an authenticated request from the endpoint device. Alternatively, the state object may be retrieved from the client device during a subsequent web session in response to an authenticated request from a host.

Abstract: A method of generating a natural language model for use in a spoken dialog system is disclosed. The method comprises using sample utterances and creating a number of hand crafted rules for each call-type defined in a labeling guide. A first NLU model is generated and tested using the hand crafted rules and sample utterances. A second NLU model is built using the sample utterances as new training data and using the hand crafted rules. The second NLU model is tested for performance using a first batch of labeled data. A series of NLU models are built by adding a previous batch of labeled data to training data and using a new batch of labeling data as test data to generate the series of NLU models with training data that increases constantly. If not all the labeling data is received, the method comprises repeating the step of building a series of NLU models until all labeling data is received.

Abstract: A voice-enabled help desk service is disclosed. The service comprises an automatic speech recognition module for recognizing speech from a user, a spoken language understanding module for understanding the output from the automatic speech recognition module, a dialog management module for generating a response to speech from the user, a natural voices text-to-speech synthesis module for synthesizing speech to generate the response to the user, and a frequently asked questions module. The frequently asked questions module handles frequently asked questions from the user by changing voices and providing predetermined prompts to answer the frequently asked question.

Abstract: A system for understanding entries, such as speech, develops a classifier by employing prior knowledge with which a given corpus of training entries is enlarged threefold. A rule is created for each of the labels employed in the classifyier, and the created rules are applied to the given corpus to create a corpus of attachments by appending a weight of ?p(x), or 1??p(x), to labels of entries that meet, or fail to meet, respectively, conditions of the labels' rules, and to also create a corpus of non-attachments by appending a weight of 1??p(x), or ?p(x), to labels of entries that meet, or fail to meet conditions of the labels' rules.