The present invention discloses a system, apparatus, and method that obtains audio and metadata information from voice calls, generates textual transcripts from those calls, and makes the resulting data searchable via a user interface. The system converts audio data from one or more sources (such as a telecommunications provider) into searchable usable text transcripts. One use of which is law enforcement and intelligence work. Another use relates to call centers to improve quality and track customer service history. Searches can be performed for callers, callees, keywords, and/or other information in calls across the system. The system can also generate automatic alerts based on callers, callees, keywords, phone numbers, and/or other information. Further the system generates and provides analytic information on the use of the phone system, the semantic content of the calls, and the connections between callers and phone numbers called, which can aid analysts in detecting patterns of behavior, and in looking for patterns of equipment use or failure.

A method may include obtaining first audio data originating at a first device during a communication session between the first device and a second device. The method may also include obtaining an availability of revoiced transcription units in a transcription system and in response to establishment of the communication session, selecting, based on the availability of revoiced transcription units, a revoiced transcription unit instead of a non-revoiced transcription unit to generate a transcript of the first audio data. The method may also include obtaining revoiced audio generated by a revoicing of the first audio data by a captioning assistant and generating a transcription of the revoiced audio using an automatic speech recognition system. The method may further include in response to selecting the revoiced transcription unit, directing the transcription of the revoiced audio to the second device as the transcript of the first audio data.

Artificial agents utilized for voice interactions continue to improve in their capacity to conduct more sophisticated interactions. Rather than just presenting a limited set of options, artificial agents are continuing to narrow the gap between generated speech and natural human speech. A requirement is often in place that spoken interactions be recorded, however, storing speech, even with data compression, is a resource-demanding task. Generated speech may be provided from content, such as text, and speech data. By recording an identifier of the content and associated speech data, storage processing and space requirements can be greatly reduced. Playback may be provided from a waveform of audio provided by the human participant and by selecting the content associated with the content identifier and generating speech of the content utilizing settings provided by the speech data.

A user interface for virtual assistant interactions on a telephony device may be provided. First, a plurality of lines associated with the telephony device, including a designated line for a user and a shared line for a virtual assistant, may be displayed through the user interface. Next, in response to receiving an incoming call to the designated line, a plurality of features associated with handling the incoming call, including an assistant feature to direct the incoming call to the virtual assistant, may be displayed through the user interface. Then, in response to the incoming call being directed to the virtual assistant, a plurality of features associated with managing a conversation between the virtual assistant and a caller during the incoming call may be displayed through the user interface. After the incoming call has ended, a call history associated with the incoming call may be displayed through the user interface.

A process for updating a second agent about a call in a contact center comprises receiving a call at the contact center and connecting the call to a device associated with a first agent of the contact center. A processor is used to configure a list of keywords to detect during the call, and when a key word is detected (e.g., using a speech analyzer), a snippet of the call based on the detected keywords is identified. The snippets are presented to a second agent through a device associated with the second agent. The call is then connected to the device associated with the second agent.

A computer-implemented method and supporting system transcribes spoken words being monitored from a telephonic interaction among two or more individuals. Telephonic interactions among the individuals are monitored, and at least two of the individuals are each assigned to a separate channel. While still being monitored, each of the channels is assigned a context-based speech recognition models, and in substantially real-time, the monitored telephonic interaction is transcribed from speech to text based on the different assigned models.

While a teleconference is occurring, data of a teleconference is analyzed to determine first participant data associated with a first speaker and second participant data associated with a second speaker. At a different application, addition of a first speaker indicator and a second speaker indicator to a text entry of a user is caused, the first speaker indicator added concurrently with identification that the first speaker is speaking and the second speaker indicator added concurrently with identification that the second speaker is speaking. At the different application, addition of key information to a text entry of a user is caused, the key information comprising participant data associated with the first speaker and second participant data associated with the second speaker.

Disclosed embodiments provide techniques for generating a summary of a voice call between two or more participants. Computer-implemented natural language processing analyzes a call transcript and generates a summary and one or more keywords associated with the transcript. The summary and keywords are included in call log history entries, allowing a user to conveniently review a summary of what was discussed on a previous voice call. Embodiments interface with a teleconference system to include assets associated with the call, such as shared documents, images, and other media files.

In an example of this disclosure, a method may include receiving, by a database server, a data write request. The data write request may include authentication information corresponding to a first call session and first additional information. The method may include generating, by the database server, a first unique identifier based on the first additional information. The authentication information may correspond to the first unique identifier. The method may include storing the first unique identifier and the authentication information in a data structure in a memory of the database server.

Methods are provided for routing communications between different recipients at an entity having access to a shared communication log and using presence information. The methods include receiving a communication from a user to an entity by a primary recipient at a call center for the entity, obtaining identifying information for the user, storing a communication log regarding the communication of the user, identifying a current presence of a secondary recipient for the entity, transferring the communication from the primary recipient to the secondary recipient in response to the presence identification of the secondary recipient indicating the secondary recipient is accessible, updating the communication log with information regarding the transfer from the primary recipient to the secondary recipient, and providing the communication log to the secondary recipient during the communication between the first user and the primary recipient or secondary recipient.