Abstract: The present invention can include a method for tuning grammar option weights of a phrase-based, automatic speech recognition (ASR) grammar, where the grammar option weights affect which entries within the grammar are matched to spoken utterances. The tuning can occur in an unsupervised fashion, meaning no special training session or manual transcription of data from an ASR session is needed. The method can include the step of selecting a phrase-based grammar to use in a communication session with a user wherein different phrase-based grammars can be selected for different users. Feedback of ASR phrase processing operations can be recorded during the communication session. Each ASR phrase processing operation can match a spoken utterance against at least one entry within the selected phrase-based grammar. At least one of the grammar option weights can be automatically adjusted based upon the feedback to improve accuracy of the phrase-based grammar.

Abstract: A method for monitoring an Internet connection can include the step of detecting a connectivity problem with a household Internet connection. A problem contact point can be determined. A communication connection that is different from the household Internet connection can be established with the contact point. For example, a voice connection can be established with the contact point. A problem notification can be conveyed to the contact point through the established communication connection.

Abstract: A method, a system and a computer program product for determining one or more characteristics of a caller, such as the mood, gender, age, and urgency of the caller, utilizing the biometric characteristics of the caller. One or more biometric characteristics are detected when a request to place an outgoing call to one or more destinations is received at a first telecommunication device. When the request to place an outgoing call is a verbal request, one or more biometric voice samples are obtained. The biometric voice samples comprise the biometric characteristics of the caller. The biometric characteristics are extracted from the biometric voice samples, encoded into a datagram, and transmitted from the first telecommunication device to the outgoing call destination (i.e. a second telecommunication device).

Abstract: A method, system and computer-usable medium for optimizing retrieval of customer data needed to handle a call are presented. The method includes the steps of receiving a call at a data center; initiating a query for a business data related to the call; creating a key that identifies the business data related to the call; pre-fetching the business data using the key with a lookup table; caching the pre-fetched business data; attaching the key to the call; routing the call with the attached key to a desktop agent; receiving a request from the desktop agent for the pre-fetched business data; retrieving the cached pre-fetched business data; and transmitting the cached pre-fetched business data to the desktop agent.

Abstract: A method implemented in a computer infrastructure having computer executable code having programming instructions tangibly embodied on a computer readable storage medium. The programming instructions are operable to receive an audio stream of a communication between a plurality of participants. Additionally, the programming instructions are operable to filter the audio stream of the communication into separate audio streams, one for each of the plurality of participants, wherein each of the separate audio streams contains portions of the communication attributable to a respective participant of the plurality of participants. Furthermore, the programming instructions are operable to output the separate audio streams to a storage system.

Abstract: A communication method can include the step of establishing a communication session between two endpoints based upon the real-time transport protocol (RTP). During the communication session, discrete packets containing digitally encoded audio can be exchanged between the two endpoints resulting in a continuous audio flow being established in real-time between the two endpoints. During the communication session, one or more of the two endpoints can convey RTP data to a remotely located RTP audio processor. The RTP data can include information necessary for the RTP audio processor to establish an audio stream with the one of the two endpoints that did not convey the RTP data to the RTP audio processor. The RTP audio processor can establish the audio stream without terminating the communication session between the two endpoints.

Abstract: Conversational biometrics and speech recognition are used by an IVR contact/call center during call hold to affect call handling/routing. A caller's (user's) behavioral response, such as an utterance or other spoken reaction to being put on hold by the IVR contact/call center, etc., can be recognized, captured and analyzed. Business rules analyze the caller's behavior in real time during a caller hold period. Such business rules can be fed back into the call center system and this information can be used to provide opportunities to affect routing priorities for a particular caller based upon information learned by the data that is captured and analyzed.

Abstract: A system and method to select and retrieve contact center transactions from a set of transactions stored in a queuing mechanism. The system includes an interactive voice response system configured to accept at least one call and dynamically populate a web form with call data associated with the at least one call. The system also includes a queuing engine configured to allow a call agent to access the call data prior to the at least one call being connected to the call agent.

Abstract: A computer implemented method, a computer program product, and a data processing system use short messaging service for extending customer service deliver channels. A message utilizing a short messaging service protocol is received from a sender. Responsive to receiving the message utilizing the short messaging service protocol, the message is parsed into a voice extensible markup language document. A virtual service request is then created from the voice extensible markup language document. Responsive to creating the virtual service request from the voice extensible markup language document, a service is requested from a message recipient, facilitated by using the virtual service request. A non-textual response is then provided to the message sender.

Abstract: A computer implemented method, a computer program product, and a data processing system provide acoustic monitoring and fault reporting. A sound is identified from a consumer device. The sound to an acoustic signal. An acoustic fingerprint is generated from the acoustic signal. The acoustic fingerprint is then compared to a threshold value to determine whether the acoustic fingerprint deviates from a threshold value by more than a defined statistical variance. If the acoustic fingerprint deviates from a threshold value by more than a defined statistical variance, notification is provided that the acoustic fingerprint deviates from the threshold value by more than the defined statistical variance.

Abstract: A method includes storing a profile associated with a user of a telephone and, based upon the profile, presenting the user with an option to search, browse, subscribe to, or bookmark content provided by a plurality of IVR content providers.

Abstract: A security method and system. The method includes receiving by a computing system, a telephone call from a user. The computing system comprises an existing password/passphrase and a pre-recorded voice sample associated with the user. The computing system prompts the user to enter a password/passphrase using speech. The computing system receives speech data comprising a first password/passphrase from the user. The computing system converts the speech data to text data. The computing system first compares the text data to the first password/passphrase and determines a match. The computing system compares the speech data to the pre-recorded voice sample to determine a result indicating whether a frequency spectrum associated with the speech data matches a frequency spectrum associated with the pre-recorded voice sample. The computing system transmits the result to the user.

Abstract: A method, system, and computer program product for efficiently comparing multiple columns of a row of a relational database to an incoming record. A computer creates a cryptographic sum for columns of a row of the relational database. The cryptographic sum is stored as a hidden column in the relational database. Logic may compare the cryptographic sum with an incoming cryptographic sum of entries in an incoming record. Logic may then determine if the incoming cryptographic sums differ from the corresponding cryptographic sums of rows of data of the relational database. When the two cryptographic sums are identical, the data of the incoming record is disregarded as an identical record that already exists. An entry of the incoming record may be added to the target table or updated within an existing record of the relational database when the cryptographic sum and the incoming cryptographic sum of that entry differ.

Abstract: A method, system, and computer program product for autonomously transcribing and building tagging data of a conversation. A corpus processing agent monitors a conversation and utilizes a speech recognition agent to identify the spoken languages, speakers, and emotional patterns of speakers of the conversation. While monitoring the conversation, the corpus processing agent determines emotional patterns by monitoring voice modulation of the speakers and evaluating the context of the conversation. When the conversation is complete, the corpus processing agent determines synonyms and paraphrases of spoken words and phrases of the conversation taking into consideration any localized dialect of the speakers. Additionally, metadata of the conversation is created and stored in a link database, for comparison with other processed conversations. A corpus, a transcription of the conversation containing metadata links, is then created.

Abstract: A mechanism for using information in an execution context and other information to optimally select a business service implementation and service execution path. Responsive to receiving a request for a service from a service requester, an execution context is created, wherein the execution context comprises information about business aspects and operational aspects of the service being requested. The request is sent with the execution context to a next component in the service request/response flow in the service oriented architecture. Responsive to the next component receiving the request, current execution context information about the service is obtained based on a current processing of the request for the service and historical execution context information about the service based on previous processing of requests for the service. A service execution decision is then made based on the current execution context information and the historical execution context information.

Abstract: A method of providing a translation within a voice stream can include receiving a speech signal in a first language, determining text from the speech signal, translating the text to a second and different language, and encoding the translated text within the speech signal.

Abstract: An administration method and system. The method includes receiving by a computing system, a telephone call from an administrator. The computing system presents an audible menu associated with a plurality of computers to the administrator. The computing system receives from the administrator, an audible selection for a computer from the audible menu. The computing system receives from the administrator, an audible verbal command for performing a maintenance operation on the computer. The computing system executes the maintenance operation on the computer. The computing system receives from the computer, confirmation data indicating that the maintenance operation has been completed. The computing system converts the confirmation data into an audible verbal message. The computing system transmits the second audible verbal message to the administrator.

Abstract: A method of call route determination based upon a statistics-based business intelligence engine (BEI) queried by an IVR subsystem with caller parameters descriptive of the caller to determine a next best route for a received call, when the default or best route for the call exceeds a threshold time. A call is received at a contact center from a caller. Content and identity information of the caller is extracted from the received call. IVR determines a first estimated wait time associated with a default route of the received call. If the first estimated wait time is greater than a threshold time, and thus unacceptable, then the IVR queries a business intelligence engine (BIE) with caller parameters descriptive of the caller to determine a next best route of the received call, with the next best route having a second estimated wait time less than the first estimated wait time of the default route. The caller is then routed to the next best route.

Abstract: A supervisor computer directly communicates, via User Datagram Protocol (UDP) packets, with a call control application software in a soft phone. The UDP packets provide real-time information, from a desktop of the soft phone, describing call activity and usage status of the soft phone. The supervisor computer is able to remotely control usage of the soft phone according to information provided by the UDP packets.

Abstract: A call directing system receives an incoming call from a caller. The caller is prompted to speak, thus enabling a prosody analyzer to generate an analysis of a prosody of the caller's voice. This analysis provides a basis for generating a caller profile that describes caller preferences of the caller. Based on the analysis of the prosody of the caller's voice and the generated caller profile, the call is directed to a particular call recipient.