Abstract: In an approach for conversational interchange optimization, a processor monitors conversations in a communication system. A processor generates a list of topics in the conversations. A processor determines a flow for each topic based on length of time, number of participants, and sentiment associated to each topic. The flow is the progress of interactions and shifts for each topic. A processor builds a statistical model for each topic based on the flow to predict success or failure of a topic progression for an incoming conversation. A processor updates the topic progression for the incoming conversation based on the predicted success or failure.

Abstract: A system for capturing and processing portions of a spoken utterance command that may occur before a wakeword. The system buffers incoming audio and indicates locations in the audio where the utterance changes, for example when a long pause is detected. When the system detects a wakeword within a particular utterance, the system determines the most recent utterance change location prior to the wakeword and sends the audio from that location to the end of the command utterance to a server for further speech processing.

Abstract: A system for categorizing words into clusters includes a receiver to receive a set of sentences formed by a plurality of words. The set of sentences is indicative of interaction of a user with a virtual assistant. A categorizer categorizes the plurality of words into a first set of clusters by using a first clustering technique, and categorizes the plurality of words into a second set of clusters by using a second clustering technique. A detector detects words that appear in similar clusters after categorization by the first clustering technique and the second clustering technique. Similarity of clusters is based on a nature of words forming the clusters. A generator generates a confidence score for each of the plurality of words based on the detection. The confidence score of a word is indicative of accuracy of the categorization of the word.

Abstract: Embodiments provide an oversight mechanism using eye tracking to monitor a human agent's review of artificial intelligence generated contact in a contact center communication session. Content generated by an artificial intelligence engine for each session can be presented to the human agent through a user interface for review by the human agent. While the generated content is being presented, an eye tracking system associated can monitor review of the generated content by the human agent. An indication of the human agent's level of attention to the generated content can be generated based on monitoring the review of the content by the human agent. The indication of the human agent's level of attention can be stored in a set of Key Performance Indicators (KPIs) for the human agent. One or more reports can be provided based on the KPIs.

Abstract: A computer-implemented method includes scanning a clip of messages that includes message requests and message responses arranged in a sequence. The scanning is performed based on one or more search parameters and produces a list of one or more name/value pairs. The clip is utilized to perform a load test on a target website. Each name/value pair has a corresponding value. For each name/value pair in the list a message request in the clip is identified where the corresponding value is first used. Then, looking backwards in the sequence from the message request where the corresponding value is first used, prior message responses are located where the corresponding value is found. An extraction point is specified in the clip for the corresponding value as a latest message response in the sequence where the corresponding value was returned from the target website. The corresponding value is then stored as a property.

Abstract: A method of managing visual voice mail in a multi-screen environment. The method includes receiving voice mail messages in a server, creating a state machine for each message, pushing a visual voice mail notification to at least three devices, receiving an action command from one of the three devices and updating the state machine responsive to the receiving step.

Abstract: There are provided systems and method for unit test automation for business rules and applications. A service provider, such as a payment provider, may wish to integrate software and platforms offered by Pegasystems, Inc., in particular Pega RULES Process (“PRPC), which offers a business process management system. PRPC allows the service provider to create and manage business rules and build business applications and platforms, such as a customer support platform. In order to provide a more flexible and comprehensive automated unit testing mechanism, a Java framework may be utilized that runs test cases in PRPC for the business rules. The Java framework may feed data into test cases and may enable dynamic data to be entered for the test cases. Additionally, the Java framework may allow for editing of data for the PRPC test cases and may allow the test cases to be reused and deleted.

Abstract: Apparatuses, systems, methods, and computer program products are disclosed for an automated messaging response. A message parsing module may parse a textual message to determine whether the message includes a question. A question determination module may determine a question type for the question. A response presentation module may present a response interface that includes a plurality of selectable responses to the question.

Abstract: In one embodiment, a communication is established between two endpoints. The communication session may be a video call or an audio call. The communication session may be managed by a call manager using, for example, voice over internet protocol and session initiation protocol. One of the endpoints initiates recording the communication session. The call manager facilitates recording the communication session based on a recording policy associated with the initiating endpoint. The recording policy may specify far end recording, near end recording, or a prioritized order of far and near end recording. The call manager selected an anchor network device for copying the communication session based on the recording policy.

Abstract: Voice call continuity is provided for calls that are carried over a hybrid network infrastructure in which access connections are distributed over loosely coupled network portions including a backend network such as a core VoIP (Voice over Internet Protocol) service network, one or more cellular mobile networks, and a public switched telephone network (“PSTN”). The calls are routed through the core VoIP network regardless of their points of origination or termination in other network portions so that signaling and call context are anchored in the core VoIP network. The conditions under which user equipment operate are continuously monitored so that when a connection is determined to have been unacceptably degraded or is likely to be interrupted, and/or a more optimal connection is available, a handover of the call to another connection is initiated so that call continuity is maintained using the lowest cost connection that provides acceptable call quality.

Abstract: A system for automated audio quality testing, having various endpoint emulators, call engines, audio generator devices, and head and torso simulator devices. The call engine utilizes reference audio samples to simulate customer interactions with a contact center. The endpoint manager utilizes reference audio samples to simulate contact center agents' interactions with customers.

Abstract: A method of managing visual voice mail in a multi-screen environment. The method includes receiving voice mail messages in a server, creating a state machine for each message, pushing a visual voice mail notification to at least three devices, receiving an action command from one of the three devices and updating the state machine responsive to the receiving step.

Abstract: A system that incorporates teachings of the present disclosure may include, for example, a method that involves receiving an indication that communications with a subscriber have been interrupted while engaged in voicemail processing, and recording a pointer to a last state of voicemail processing. Additional embodiments are disclosed.

Abstract: Embodiments are provided for the automatic real-time recording and processing of media in a communications network based on the context of the media. In one embodiment, a media stream is received in an analysis module in a service platform in the communications network. The media stream may represent a communication session between a calling party and a call center in the network. The incoming media steam is analyzed to identify words comprising a context of the communication session. A determination is then made as to whether the context of the communication session is related to a set of business rules associated with the service platform which may automatically trigger the retention of a recording of the communication session. If the context of the communication session is related to the set of business rules, the retention of the communication session is automatically triggered in real-time at a recording module.

Abstract: Provided are an apparatus and method for reporting speech recognition failures. The method includes detecting pure speech data from input speech data and outputting the detected pure speech data; checking at least one speech recognition failure for the pure speech data; and ascertaining speech recognition failure reasons from a check-result for the speech recognition failures and outputting the ascertained speech recognition failure reasons.

Abstract: A method and apparatus of processing a customer call is disclosed. The customer call may be initiated for an interactive voice response (IVR) type call system. One example method may include processing an interactive voice response (IVR) customer call. The method may include receiving customer call input to IVR call menu prompts, evaluating customer call interactions with the IVR call menu prompts, and calculating at least one usability score of the customer's interactions with the IVR call menu prompts. The method may also include displaying the results of the at least one usability scores on a user interface.

Abstract: Embodiments are provided for the automatic real-time recording and processing of media in a communications network based on the context of the media. In one embodiment, a media stream is received in an analysis module in a service platform in the communications network. The media stream may represent a communication session between a calling party and a call center in the network. The incoming media steam is analyzed to identify words comprising a context of the communication session. A determination is then made as to whether the context of the communication session is related to a set of business rules associated with the service platform which may automatically trigger the retention of a recording of the communication session. If the context of the communication session is related to the set of business rules, the retention of the communication session is automatically triggered in real-time at a recording module.

Abstract: Described is a system and method for processing a voice mail. The method comprises receiving a voice mail, converting the voice mail into a text message using a predefined speech-to-text conversion algorithm and transmitting the text message to a wireless computing device.

Abstract: A method and a processing device for managing an interactive speech recognition system is provided. Whether a voice input relates to expected input, at least partially, of any one of a group of menus different from a current menu is determined. If the voice input relates to the expected input, at least partially, of any one of the group of menus different from the current menu, skipping to the one of the group of menus is performed. The group of menus is different from the current menu include menus at multiple hierarchical levels.

Abstract: A facility and method for analyzing and classifying calls without transcription. The facility analyzes individual frames of an audio to identify speech and measure the amount of time spent in speech for each channel (e.g., caller channel, agent channel). Additional telephony metrics such as R-factor or MOS score and other metadata may be factored in as audio analysis inputs. The facility then analyzes the frames together as a whole and formulates a clustered-frame representation of a conversation to further identify dialogue patterns and characterize call classification. Based on the data in the clustered-frame representation, the facility is able to make estimations of call classification. The correlation of dialogue patterns to call classification may be utilized to develop targeted solutions for call classification issues, target certain advertising channels over others, evaluate advertising placements at scale, score callers, and to identify spammers.

Abstract: Systems, methods, apparatus, and computer program products are provided for scheduling and initiating calls. For example, a request for a prospective call between a caller and a callee can be received via a server. The prospective call can be electronically added to call lists associated respectively with the caller and the callee. In response to a determination that both the caller and the callee are available, a call between a caller device and a callee device can be automatically initiated.

Abstract: A portable electronic device is provided. The portable electronic device comprises a processor, a memory, and a capturing application stored in the memory that, when executed on the portable electronic device, monitors a first voice telephone call with a first transmitting device. The portable electronic device also comprises records a telephone number spoken during the first voice telephone call. The portable electronic device also comprises sends a first message to the first transmitting device, the first message containing the telephone number and requesting confirmation of the telephone number. The portable electronic device comprises receives a second message from the first transmitting device, the second message confirming the telephone number.

Abstract: A voicemail system (100) can include at least one processor (104) and at least one communication interface (102) operatively linked and in communication with the at least one processor (104) that is configured to receive an incoming call. The voicemail system (100) can further include at least one memory (108) operatively linked and in communication with the processor (104), wherein the at least one memory (108) is configured to store a call treatment application (112) that includes at least one rule for determining call handling treatment of the incoming call. A method (400) for operating the voicemail system (100) can include receiving (406) an address message (200) at the voicemail system (100), wherein the address message (200) identifies at least a called party number (206) of the incoming call.

Abstract: Embodiments of the present invention are directed to a recording method, and, corresponding to the recording method, a recording device and an electronic device. The recording method of the embodiments of the present invention is applicable in a first electronic device, where the first electronic device comprises a voice communication unit. The recording method comprises performing a voice communication with a second electronic device via the voice communication unit; during the voice communication, receiving a record command from a user; on the basis of the record command, performing a content recording and generating record data; generating communication identity information on the basis of the voice communication; when the content recording is completed, generating a record file via the record data, and correlating the communication identity information to the record file.

Abstract: A method implemented to provide voice calls in a network. The method comprises receiving a voice call initiation request at a caller agent, wherein the voice call initiation request is triggered by a caller initiating a voice call via a caller equipment, wherein the voice call is destined to a callee equipment communicatively coupled with the network to reach a caller, and wherein the caller agent and a callee agent interact with the caller equipment and the callee equipment respectively. The method further comprise sending a call connection message to the caller equipment, receiving an acknowledgment message from the caller equipment, and opening a voice channel between the caller and the caller agent without waiting for a callee agent response.

Abstract: An apparatus and method for schedule management includes storing at least one schedule for a user. The current activity of the user is determined. At a remind time for each schedule, the user is reminded of the schedule according to a reminder method. The reminder method selection is based on at least the determined current activity of the user. Some of the reminder methods selected between may include, for example, voice, ring, vibration, light, and/or text.

Abstract: In one embodiment, a method for ensuring quality of a media message is provided. The method includes receiving information for a media message. At least a portion of the media is analyzed to determine a media quality for the media message. The method then determines if the media quality is acceptable. If the media quality is not acceptable, then an alert may be sent regarding the media quality of the media message. For example, a caller may be prompted to re-record a media message.

Abstract: A voicemail system (100) can include at least one processor (104) and at least one communication interface (102) operatively linked and in communication with the at least one processor (104) that is configured to receive an incoming call. The voicemail system (100) can further include at least one memory (108) operatively linked and in communication with the processor (104), wherein the at least one memory (108) is configured to store a call treatment application (112) that includes at least one rule for determining call handling treatment of the incoming call. A method (400) for operating the voicemail system (100) can include receiving (406) an address message (200) at the voicemail system (100), wherein the address message (200) identifies at least a called party number (206) of the incoming call.

Abstract: Inmate communications systems provide a feature-rich platform with a high degree of flexibility and security employing call control facilities located of institutional premises. Authentication processes for calling and called party verification include biometric techniques in some embodiments. Distributed processing of call control and billing provide flexible interactive call payment processes. Preferred embodiments feature voice over IP transmission and control featuring controlled access to avoid addition of unauthorized third-party call participants. Monitoring, recording and selective forwarding of calls is provided under control of system administrators.

Abstract: The invention provides a system and method for indexing and organizing voice mail message by the speaker of the message. One or more speaker models are created from voice mail messages received. As additional messages are left, each of the new messages are compared with existing speaker models to determine the identity of the callers of each of the new messages. The voice mail messages are organized within a user's mailbox by caller. Unknown callers may be identified and tagged by the user and then used to create new speaker models and/or update existing speaker models.

Abstract: The present invention discloses a method and a system for implementing an MRBT service, comprising: Step S102, a calling terminal initiates a call to a called terminal which has registered a multimedia MRBT service, and triggers an MRBT service module of the MRBT Application Server according to service template information subscribed in a Home Subscriber Server by the called terminal; Step S104, the MRBT service module calls the called terminal through an IMS network, and performs query on an MRBT platform according to the call related information to obtain the MRBT information to be played for the calling terminal; and Step S106, the calling terminal performs negotiation with the MRBT platform and performs negotiation with the called terminal, and the MRBT platform plays the MRBT information inquired by the MRBT service module according to the call related information to the calling terminal on condition that the negotiations are successful.

Abstract: A method is disclosed for associating a caller utterance with corresponding elements of a flowgraph that depicts a voice-response system. Thus, an analyst who selects an element in a flowgraph receives immediate access to those utterances—and only those utterances—that are associated with the selected element. The analyst can easily listen to the utterances and review statistics associated with them. The utterances are stored, retrieved, and presented in a systematic and organized way. In some embodiments in accordance with the present invention, an utterance is associated with the link between two events in the voice-response system. In some alternative embodiments, an utterance is associated with other data, including, but not limited to: the event that precedes it; the event that follows it; the telephone number of the caller.

Abstract: A system and method is provided for receiving a voice message, selecting from multiple destinations, transmitting the voice message to a destination and subsequently playing back the voice message after it has been received by the destination. The system has a plurality of access devices which are coupled to each other over a network such as the Internet. These access devices may include computers, workstations, and the like. Access devices may include a voice conversion board for converting a voice message received over a network into a voice signal for playback to a telephone device.

Abstract: Systems and methods for the matching of datasets, such as input audio segments, with known datasets in a database are disclosed. In an illustrative embodiment, the use of the presently disclosed systems and methods is described in conjunction with recognizing known network message recordings encountered during an outbound telephone call. The methodologies include creation of a ternary fingerprint bitmap to make the comparison process more efficient. Also disclosed are automated methodologies for creating the database of known datasets from a larger collection of datasets.

Abstract: The present invention provides methods, devices, and systems for notifying a caller that they are leaving a low quality voice mail. The user can be notified that they are leaving such a voicemail before they are done leaving the message. This allows the user to try and leave another voicemail having a better quality, thereby making the voicemail more comprehensible.

Abstract: A method including receiving a voice call; analyzing speech in real-time to determine whether payment information is included in the voice call; omitting to record the voice call when it is determined that the voice call includes the payment information; and recording the voice call when it is determined that the voice call does not include the payment information.

Abstract: A method can include detecting an incoming voice mail message and accessing information associated with the incoming voice mail message. The information associated with the incoming voice message may then be compared with some other information, which may comprise one or more of these attributes associated with each message: a caller ID; a time stamp; a user extension; a message length; a caller identification; message content; and whether a user has tagged each message as spam.

Abstract: Handling an incoming call from a caller to a user includes prompting a caller to record a message to the user and sending a special command to a user communication device indicting that the incoming call is available for screening and retrieving. In response to the user indicating a desire to screen the incoming call, the user listens to the message while the caller is leaving the message. In response to the user indicating a desire to retrieve the incoming call, the call is transferred to the user communication device. In response to the user indicating a desire to screen the call, an incoming media stream from the incoming call may be forked so that the message is being recorded while the user is listening to the message at the user communication device.

Abstract: A communication system provides a user with the ability to redirect telephone calls to a voice chat account and vice versa. In one example, a voice chat gateway may receive communication requests and determine whether communications directed to a first party is to be redirected. If so, the voice chat gateway may reroute the communication request to an appropriate destination. For instance, a user may request that all communications such as telephone calls be rerouted as a voice chat to the user's voice chat account. Alternatively, a user may request that all communications including voice chats be redirected to a telephone number. Users may further be allowed to call a voice chat account through a telephone network and initiate a voice chat with a telephone number through a data network.

Abstract: A computing device may extract keywords from a phone call or other audio communication and later display those keywords in a call log or in a caller ID. In one example, a method performed by at least one processor of a first computing device includes receiving speech inputs during an audio communication between the first computing device and a second device. The method further includes performing speech-to-text processing on the speech inputs to generate text based on the speech inputs. The method further includes performing keyword extraction processing on the text to generate one or more keywords based on the text, that score highly as relevant indicators of the audio communication, based on one or more keyword extraction criteria. The method further includes storing the one or more keywords in association with identifying information associated with the second device.

Abstract: The present solution can include a method for using dialog contracts for contact center interactions. The method can include a step of determining a context that applies to a caller who is communicating with a contact center. A dialog contract can be identified that corresponds to the determined context. The dialog contract can specify requirements for a real-time contact center session. The contact center can transfer the caller to a contact center agent. The real-time communication session can be conducted. A software program, referred to as an agent monitor, can analyze input of the caller and the contact center agent during the communication session and can automatically update a session file as requirements of the dialog contract are satisfied. The session file can be used as a quality measurement of the communication session.

Abstract: A system and method for efficiently transcribing verbal messages to text is provided. Verbal messages are received and at least one of the verbal messages is divided into segments. Automatically recognized text is determined for each of the segments by performing speech recognition and a confidence rating is assigned to the automatically recognized text for each segment. A threshold is applied to the confidence ratings and those segments with confidence ratings that fall below the threshold are identified. The segments that fall below the threshold are assigned to one or more human agents starting with those segments that have the lowest confidence ratings. Transcription from the human agents is received for the segments assigned to that agent. The transcription is assembled with the automatically recognized text of the segments not assigned to the human agents as a text message for the at least one verbal message.

Abstract: Techniques are described for providing relevant information to users (e.g., information that is at least potentially of interest to the users). Relevant information for a user may be automatically determined based on a determined context of the user and/or on a request for that information from the user. For example, voice-based information may be obtained from a user in one or more ways, and then analyzed to identify requests or other indications of information of interest and/or to otherwise determine a context of the user that corresponds to potential information of interest. Relevant information for a user may be provided to the user in various ways, such as via a voice-based response during a telephone call and/or via one or more electronic messages sent to the user (e.g., via emails, instant messages, paging messages, SMS or other text messages, etc.).

Abstract: A voice communication apparatus includes an analysis unit to analyze an outgoing conversation signal transmitted from a user of the voice communication apparatus to another party in communication or an incoming conversation signal from the another party in communication received by the voice communication apparatus, a storage unit to store a voice message to be played back, a mixing unit to perform mixing of the voice message with the incoming conversation signal, and a control unit to control a start timing of the mixing so that the mixing of the voice message with the incoming conversation signal is started between utterances of the user on the basis of an analysis result of the analysis unit.

Abstract: A computer-implemented system and method for processing audio in a voice response environment is provided. A database of host scripts each comprising signature files of audio phrases and actions to take when one of the audio phrases is recognized is maintained. The host scripts are loaded and a call to a voice mail server is initiated. Incoming audio buffers are received during the call from voice messages stored on the voice mail server. The incoming audio buffers are processed. A signature data structure is created for each audio buffer. The signature data structure is compared with signatures of expected phrases in the host scripts. The actions stored in the host scripts are executed when the signature data structure matches the signature of the expected phrase.

Abstract: A method and a processing device for managing an interactive speech recognition system is provided. Whether a voice input relates to expected input, at least partially, of any one of a group of menus different from a current menu is determined. If the voice input relates to the expected input, at least partially, of any one of the group of menus different from the current menu, skipping to the one of the group of menus is performed. The group of menus different from the current menu include menus at multiple hierarchical levels.

Abstract: The invention provides a system and method for indexing and organizing voice mail message by the speaker of the message. One or more speaker models are created from voice mail messages received. As additional messages are left, each of the new messages are compared with existing speaker models to determine the identity of the callers of each of the new messages. The voice mail messages are organized within a user's mailbox by caller. Unknown callers may be identified and tagged by the user and then used to create new speaker models and/or update existing speaker models.

Abstract: Devices, systems, and methods for recording call sessions over a VoIP network using a distributed record server architecture are disclosed. An example recording device for recording segments of a call session includes a record server configured to receive an agent voice data stream and an external caller voice data stream from an agent telephone station, and a file repository configured to store voice data and call data associated with each recorded segment of the call session. The recording device is configured to tag recorded segments of each call session, which can be later used by a third-party application or database to check the status and/or integrity of the recorded call session.

Abstract: Embodiments are provided for the automatic real-time recording and processing of media in a communications network based on the context of the media. In one embodiment, a media stream is received in an analysis module in a service platform in the communications network. The media stream may represent a communication session between a calling party and a call center in the network. The incoming media steam is analyzed to identify words comprising a context of the communication session. A determination is then made as to whether the context of the communication session is related to a set of business rules associated with the service platform which may automatically trigger the retention of a recording of the communication session. If the context of the communication session is related to the set of business rules, the retention of the communication session is automatically triggered in real-time at a recording module.

Abstract: A mobile communication terminal includes timer for detecting the time of an incoming call, a caller number registration table for storing caller numbers, answer message ID numbers and time-dependent switching codes in relation to each other, the time-dependent control codes designating callers for whom answer messages are switched depending on a time zone in which the call is made. There is thus provided a capability of selecting an answer message for a caller based on the caller number included in the incoming call signal and switching between answer messages based on the time of call incoming detected by the timer.