A language proficiency analyzer automatically evaluates a person's language proficiency by analyzing that person's oral communications with another person. The analyzer first enhances the quality of an audio recording of a conversation between the two people using a neural network that automatically detects loss features in the audio and adds those loss features back into the audio. The analyzer then performs a textual and audio analysis on the improved audio. Through textual analysis, the analyzer uses a multi-attention network to determine how focused one person is on the other and/or how pleased one person is with the other. Through audio analysis, the analyzer uses a neural network to determine how well one person pronounced words during the conversation.

A computerized VoIP system which provides a computerized service for facilitating face-to-face and/or telephone meetings, in real time, between persons lacking a common language or having language barriers such as accents and dialects e.g. by utilizing or generating a networked worldwide community of Simultaneous Interpreters, using e.g. POTS (Plain Old Telephone Service), Smart Phone or any mobile phone. A platform may thereby be provided for professional simultaneous interpreters and business/private people, where interpreters from all over the world may translate any face-to-face meeting or telephone call between business people in any combination of languages, in real time.

A method to transcribe communications includes the steps of obtaining a plurality of hypothesis transcriptions of a voice signal generated by a speech recognition system, determining consistent words that are included in at least first and second of the plurality of hypothesis transcriptions, in response to determining the consistent words, providing the consistent words to a device for presentation of the consistent words to an assisted user, and presenting the consistent words via a display screen on the device, wherein a rate of the presentation of the words on the display screen is variable.

In some implementations, a system may receive an audio stream associated with a call between a user and an agent. The system may process, by the device and using a speech alteration model, speech from a first channel of the audio stream to alter the speech from having a first speech characteristic to having a second speech characteristic, wherein the speech alteration model is trained based on reference audio data associated with the first speech characteristic and the second speech characteristic and based on reference speech data associated with the first speech characteristic and the second speech characteristic. The system may extract the speech from the first channel that has the first speech characteristic. The system may provide, within a second channel of the audio stream, altered speech that corresponds to the speech and that has the first speech characteristic.

Secure system and method of detecting and preventing inmate to inmate message relays. A system and method which monitors inmate communications for similar phrases that occur as part of two or more separate inmate messages. These similar phrases may be overlapping in real time as in a conference call or can occur at separate times in separate messages. The communications that appear similar are assigned a score and the score is compared to a threshold. If the score is above a certain threshold, the communication is flagged and remedial actions are taken. If the flagged communication contains illegal matter then the communication can be disconnected or restricted in the future.

Systems and methods are provided for dynamic routing of an automated telephony system. The automated telephony system facilitates functions desired by a caller, via an automated call with the caller. A machine-learning analysis system extracts data from the automated call, performs machine-learning via the extracted data to identify a likely motivation of the caller associated with the automated call, and provides the likely motivation to the automated telephony system. The automated telephony system then receive the likely motivation from the machine-learning analysis system and dynamically routes the automated call based upon the likely motivation.

A method for creating a push notification at a call center includes: receiving a call from a caller device; receiving, from the caller device, caller identification information; receiving, from the caller device, an inquiry; generating an encrypted token including the caller identification information and the inquiry; and when an agent is available, sending a push notification to the caller device for connecting the caller to the agent, the push notification being associated with the encrypted token, and wherein the agent uses the caller identification information from the encrypted token when the agent is addressing the inquiry.

A computer based system and method for identifying complaint interactions, including: detecting appearances of linguistic structures related to complaints in an interaction; calculating at least one sentiment metric of the interaction; and classifying the interaction as being or not being a complaint interaction based on the detected linguistic structures and the at least one sentiment metric, for example using a trained supervised learning model.

A computer implemented language interpretation/translation platform is provided. The computer implemented language interpretation/translation platform comprises a processor that receives a request from a mobile computing device for a voice-based language interpretation/translation session. Further, the processor determines a potential language interpreter/translator to perform language interpretation/translation based upon the request. In addition, the processor sends a non-voice augmented feature that is associated with the potential language interpreter/translator to the mobile computing device so that the mobile computing device renders the non-voice augmented feature on a display device of the mobile computing device. The processor also receives an indication from the mobile computing device that the potential language interpreter/translator is accepted by a user associated with the mobile computing device. Further, the processor establishes the voice-based language interpretation/translation session between the mobile device and a communication device associated with the potential language interpreter/translator.

Different call managing techniques are described for both voice calls and video calls. A call management system detects that a user is on an active call. The call management system detects that the user has continued to speak when the call was disconnected, as by another user terminating the call or poor network conditions. When the call management system detects a disconnected call, it records the spoken speech into a buffer and determines which portion of the user's speech was not processed and communicated to the other user. The user whose call was terminated is provided with an option to provide the un-communicated speech to the other user. Options can include sending a text version of the un-communicated speech to the other user or sending a voice file to the other user.