Abstract: Systems and methods for providing one-to-one and audio and video calls or for providing multi-party audio or video conferences also provide language translation services. When language translation services are provided, a party to a call or conference hears both the audio of the speaker, and a translated version of the speaker's audio.

Abstract: Aspects of the subject disclosure may include, for example, a device, including a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations of receiving an original audio signal for an interval; creating a time-series graphical image of the original audio signal for the interval; compressing the time-series graphical image, thereby creating a reduced resolution image; recreating a retrieved audio signal from the reduced resolution image; determining whether a comparison of the retrieved audio signal to the original audio signal meets a quality threshold; responsive to meeting the quality threshold, compressing the reduced resolution image further and repeating the recreating and determining steps; and transmitting a last reduced resolution image that meets the quality threshold. Other embodiments are disclosed.

Abstract: A speech interface device is configured with “hybrid” capabilities, which allows the speech interface device to perform actions in response to user speech, even when the speech interface device is unable to communicate with a remote system over a wide area network (e.g., the Internet). A hybrid request selector of the speech interface device sends audio data representing user speech to both a remote speech processing system and a local speech processing component executing on the speech interface device, and then waits for a response from either or both components. The local speech processing component may start execution based on the audio data and subsequently suspend the execution until further instruction from the hybrid request selector. The hybrid request selector can then determine which response to use, and, depending on which response is chosen, may instruct the local speech processing component to either continue or terminate the suspended execution.

Abstract: A generation device is a device that generates a translated sentence in a second language from an input sentence in a first language to be translated. The generation device includes: an acquisition unit that acquires the input sentence; a normalization unit that converts the input sentence into a normalized sentence that is a grammatically correct sentence in the first language; and a first translation unit that generates the translated sentence by translating the normalized sentence into the second language using first parallel translation data that is parallel translation data between the first language and the second language. The normalization unit generates the normalized sentence by using second parallel translation data that is parallel translation data between a third language and the first language. A data amount of the second parallel translation data is larger than a data amount of the first parallel translation data.

Abstract: The present invention provides systems and methods for dynamic word prediction and suggestion. The method includes an AI engine configured to render a touch-enabled keyboard interface on a display unit of the electronic device, identify a plurality of elements of an input message of a user on a messaging application and transform the input message into an array of a specific numbers based on the plurality of elements. The method further includes converting the array into a 2D matrix of embeddings by the AI engine, wherein the embeddings include semantic information of the input message to identify a context of the input message and converting the matrix into an output array with a changed dimension. The AI engine is further configured to convert the output array into probabilities of one or more words corresponding to the input message of the user on the messaging application.

Abstract: Software that performs the following operations: (i) receiving a set of graph predictions corresponding to an input text, where graph predictions of the set of graph predictions are generated by different respective machine learning models; (ii) blending the graph predictions of the set of graph predictions to generate a plurality of candidate blended graphs, where nodes and edges of the candidate blended graphs have respective selection metric values, generated using a selection metric function, that meet a minimum threshold; and (iii) selecting as an output blended graph a candidate blended graph of the plurality of candidate blended graphs having a highest total combination of selection metric values among the plurality of candidate blended graphs.

Abstract: An example process includes while an electronic device is engaged in a communication session with external device(s): receiving, from a first user of the electronic device, input to invoke a first digital assistant; receiving, from the first user, a natural language input corresponding to a task; in accordance with invoking the first digital assistant, generating, by the first digital assistant, a prompt for further user input about the task; transmitting, to the external device(s), the prompt for further user input about the task; after transmitting the prompt for further user input, receiving, from an external device of the external device(s), a response to the prompt for further user input; initiating, by the first digital assistant, based on the response and information corresponding to the first user stored on the electronic device, the task; and transmitting, to the external device(s), an output indicative of the initiated task.

Abstract: An apparatus to realize the virtual height and surround effect. The apparatus includes at least an input source, a processor and front speaker. The input source provides the input signals on front, surround and height channels input into the processor in which a beamforming, channel separation and/or virtual-height effect are applied on each of the source channels, respectively. After the processing, all produced output channels output by the processor are arranged and combined into existing speakers of the soundbar.

Abstract: A display device including a user input receiver configured to receive a user input; a voice receiver configured to receive a user voice input; a memory configured to store a plurality of Voice Assistance (VA) applications associated with a plurality of VA servers that provide a conversation service; and a processor configured to based on a user input for performing a function corresponding to at least one VA application being received through the user input receiver, perform a function corresponding to a first VA application among the plurality of VA applications stored in the memory according to setting information designating the function corresponding to the first VA to be automatically performed according to the user input, and based on a wake up word for performing a function corresponding to a second VA application among the plurality of VA applications being included in the user voice input received through the voice receiver, change the setting information stored in the memory such that the function

Abstract: Disclosed is a system for telephones by providing an improved and streamlined user experience and enhanced fail over mechanisms. A decentralized system managed through a web site which allows for continued operation even when the primary systems fail includes a mechanism for restoring the primary systems automatically when they become available again. Phones connect to two PBX systems at the same time, one local and one at a remote location. The two PBX systems synchronize configuration data and media files between them. The website can also be used to manage any number of systems allowing any size organization to manage every phone system in their organization from a single interface.

Abstract: A system, method, and computer-readable medium are disclosed for intelligent User workload orchestration for virtual meetings. A virtual meeting for multiple users is initiated. Voice data of multiple users is received and converted to text data. Machine learning processes the text data to action items to be performed by specific users (i.e., meeting attendees) in real-time. Minutes of the meeting and action items (in the form of real-time and passive recommendations) are generated and provided. In order to perform the action items, determination is made as to which third party applications support the action items and intelligent user workload orchestration is employed.

Abstract: A method includes detecting multiple users, receiving a first query issued by a first user, the first query including a command for a digital assistant to perform a first action, and enabling a round robin mode to control performance of actions commanded by queries. The method also includes, while performing the first action, receiving audio data corresponding to a second query including a command to perform a second action, performing speaker identification on the audio data, determining that the second query was spoken by the first user, preventing performing the second action, and prompting at least another user to issue a query. The method further includes receiving a third query issued by a second user, the third query including a command for the digital assistant to perform a third action, and when the digital assistant completes performing the first action, executing performance of the third action.

Abstract: Method starts with a processor receiving configuration settings including an identified task, a relationship data, and a criticality value. Processor initializes a communication session with an agent client device. The communication session is between a virtual caller associated with the system and the agent client device. Processor then processes an audio signal of the communication session to generate an agent utterance and generates a transcribed agent utterance based on the agent utterance using a speech-to-text processor. Processor generates a virtual caller utterance using a task-specific virtual caller neural network associated with the identified task. The virtual caller utterance can be generated based on the transcribed agent utterance. Processor then causes the virtual caller utterance to be played back in the communication session to the agent client device. Other embodiments are disclosed herein.

Abstract: Implementations relate to an application that can bias automatic speech recognition for meetings using data that may be associated with the meeting and/or meeting participants. A transcription of inputs provided during a meeting can additionally and/or alternatively be processed to determine whether the inputs should be incorporated into a meeting document, which can provide a summary for the meeting. In some instances, entries into a meeting document can be designated as action items, and those action items can optionally have conditions for reminding meeting participants about the action items and/or for determining whether an action item has been fulfilled. In this way, various tasks that may typically be manually performed by meeting participants, such as creating a meeting summary, can be automated in a more accurate manner. This can preserve resources that may otherwise be wasted during video conferences, in-person meetings, and/or other gatherings.

Abstract: Techniques are disclosed relating to natural language processing. In some embodiments, a computer system receives unlabeled content. In some embodiments, the computer system embeds, using a machine learning model, the unlabeled content, where the embedding generates an unlabeled vector. In some embodiments, the computer system determines, from a plurality of labeled vectors stored in a vector index, a first set of labeled vectors that match the unlabeled vector, where the first set of labeled vectors are generated from a set of labeled content stored in a database. In some embodiments, the computer system assigns a new label to the unlabeled content, where the new label is selected from the first set of labeled vectors. In some embodiments, the computer system stores the newly labeled content in the database. The disclosed techniques may advantageously provide for automatically labeling content based on its semantic rather than its syntactic meaning.

Abstract: A mobile terminal is provided, including a housing (21) and a speaker (10). The speaker (10) includes a box (11) and a sound generation unit (12). The box (11) includes a first cover body (117), a second cover body (118), and a cover plate (13). A first chamber is formed between the sounding unit (12) and the inner bottom wall of the first cover body, and a sound hole (113) is disposed in the first cavity (111). A second cavity (112) is formed between the sound generation unit (12) and the second cover body (118). The sound generation unit (12) includes a diaphragm (123). A resonant cavity (114) with a through hole (116) on one side is formed in the first cover body (117), the cover plate (13) covers the through hole (116), and a microhole (115) is disposed. Airflow enters the second cavity (112) through the microhole (115).

Abstract: A full attention mechanism of a multilingual transformer model is converted into a Longformer attention mechanism to generate a Longformer multilingual transformer model. The Longformer multilingual transformer model is finetuned to perform a summarization task based on episode-description:episode-transcript pairs, thereby generating a finetuned Longformer multilingual transformer model. The Longformer multilingual transformer model also can further be finetuned to perform a summarization task based on article-summary:full-original-article pairs. A summary of a query episode transcript can be generated using the single-finetuned Longformer multilingual transformer model and/or the double-finetuned Longformer multilingual transformer model. The multilingual transformer-based model enables systems, methods and computer products to be capable of generating multilingual abstractive summaries.

Abstract: A response method, a terminal, and a storage medium. The response method comprises: determining, at a first time point by means of speech recognition processing, a first target text corresponding to the first time point (1001); determining, according to the first target text, a first predicted intention and an answer to be pushed, wherein said answer is used for responding to speech information (1002); continuing to determine, by means of the speech recognition processing, a second target text corresponding to a second time point and a second predicted intention, wherein the second time point is the next successive time point of the first time point (1003); determining, according to the first predicted intention and the second predicted intention, whether a preset response condition is satisfied (1004); and responding according to said answer if the preset response condition is determined to be satisfied (1005).

Abstract: Techniques for performing conversation recovery of a system/user exchange are described. In response to determining that an action responsive to a user input cannot be performed, a system may determine a topic to recommend to a user. The topic may be unrelated to the original substance of the user input. The system may have access to various data representing a context in which a user provides an input to the system. The system may use these inputs and various data at runtime to make a determination regarding whether a user should be recommended a topic, as well as what that topic should be. The system may cause a question be output to the user, with the question asking the user about the topic, for example whether the user would like a song played, whether the user would like to hear information about a particular individual (e.g., artist), whether the user would like to know about a particular skill (e.g.

Abstract: A sound control device and a method for controlling the sound control device in a vehicle. The method comprises obtaining an error signal indicating residual noise in the vehicle, and an audio signal; calculating magnitudes of low frequency components of the error signal; adjusting magnitudes of low frequency components of the audio signal according to the magnitudes of the low frequency components of the error signal; and outputting the adjusted audio signal through a speaker.