A personal voice model is created using a person's voice, essentially, voice cloning. When user wants to send a message to another person from his mobile phone or similar device, the user types the message and it is converted to a speech message using the voice model created. The speech message is delivered either to a voicemail or another medium which accepts a voice message. The text can be converted to a different language as well and send a voice message in a different language.

Methods, systems, and computer programs are presented for abstractive summarization of text by viewing sequence transduction as a language modeling problem. One method comprises an operation for training a machine-learning program to create a machine-learning model that estimates a word to be added to a running summary for the text being summarized. The method further comprises operations for detecting the text to be summarized, initializing the running summary, and performing a plurality of iterations. Each iteration comprises providing, to the machine-learning model, the source text and the running summary, and adding, using the machine-learning model, a new word to the running summary. Further, the method comprises an operation for storing, on a memory, the running summary as the summary of the text.

Method and system for group communication across electronic mail users and feature phone users. A method for receiving electronic mails on a feature phone includes receiving a text message on the feature phone in response to a first electronic mail. The method also includes calling a telephonic number embedded in the text message to listen to an audio clip of the first electronic mail and providing a voice input as a response to the first electronic mail. The system includes a feature phone that receives a plurality of electronic mails. The system also includes one or more electronic devices, and a communication interface in electronic communication with the feature phone and the one or more electronic devices. The system further includes a memory that stores instructions, and a processor responsive to the instructions to receive a text message in response to an electronic mail transmitted by an electronic mail user.

In order to provide effective communications, the individuals engaged in the communication should have appropriately matched language proficiencies. By ensuring that a customer of a contact center is matched with an agent having, or presenting, content of a communication utilizing language proficiency appropriate for the customer, effective communications may be provided. Should an agent deviate and provide communication content having language proficiency that is misaligned with the customer, automatic corrective action may be taken to realign the language proficiency presented to the customer.

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 computer-implemented method for modifying audio-based communications produced during a conference call is disclosed. The computer-implemented method can include monitoring a plurality of utterances transmitted via an audio feed of a device connected to the conference call. The computer-implemented method can identify a first unwanted audio component transmitted via the audio feed. The computer-implemented method can actively modify the audio feed by removing the first unwanted audio component from the audio feed.

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 real-time call translation system and method is provided. The invention provides establishing a voice call between a user speaking a source language and another user understanding and speaking a different target language; and performing translation of the audio of the source user into audio in the target language, and translation of the audio of the target user back to audio in the source language during the call. Further, the invention provides interlacing of the audio of the source user, the target user and the translated audio; in which the listener first hears the original audio from the other participant and then the associated translated audio and the speaker synchronously also hears the translated audio. Further the interlacing provides participants a better understanding of the conversation and conversational flow. Further the method facilitates better translations and clearer transcription, as the audio streams are not overlapped, and further noise and interference are reduced in the audio streams.

A participating terminal connection unit connects a plurality of terminals participating in communication, acquires language information set for each terminal to recognize the language used in the terminal, defines for each terminal a terminal message box for the communication, in which messages are described so as to be displayable in a time-series manner, and correlates the use language of the terminal with the terminal message box. A box coupling setting unit sets coupling between first and second terminal message boxes so that a transmission message written in the first terminal message box is translated and written in the second terminal message box as a reception message. When a transmission message is written in the first terminal message box from the first terminal, a box coupling execution unit translates the transmission message according to the coupling and writes the translated message in the second terminal message box as a reception message.

A call translation system and a method for operating the management system in a controlled environment is disclosed. The call translation system includes a calling device and a call translation server. The calling device receives authorization from the call translation server to conduct call sessions within the controlled environment. The calling device further receives a call session application from the call translation server that enables the calling device to initiate and establish call sessions through the call translation server. The call session application allows a user of the calling device to select outside parties to add to the call session.