Abstract: A system and method for omnichannel text-based routing, transfer, and customer-to-enterprise communications with smart masking of personal information. The system is a cloud-based network containing an interaction control server, a routing engine, an optimization engine, a media translation server, a mobile application, a business entity portal, mobile and compute devices for business enterprise and customer, and an enterprise database. Taken together or in part, said system optimizes customer interactions by delivering context aware text message, chat or email to customers; and when requested by customer, optimally routes with context, based upon a multitude of variables, to best available resource to handle the customer interaction. The system may be accessed through web browsers or purpose-built computer and mobile phone applications.

Abstract: A server is provided. The server includes a communication circuitry, and at least one processor operatively connected with the communication circuitry. The at least one processor may be configured to, in response to traffic of a plurality of speeches to wake up a voice assistant feature, received within a preset period being a preset value or more, generate a plurality of clusters based on similarities between the plurality of speeches, and determine whether to respond to each of speeches included in each of the plurality of clusters based on similarities between the speeches included in each of the plurality of clusters.

Abstract: An example method involves monitoring, by a computing device, a communications feed for an indication of media and detecting, in the communications feed, the indication of the media. The method may further involve identifying at least one media item corresponding to the indication of the media and causing a playback queue of a media playback system to include one or more of the identified at least one media item.

Abstract: A device and method for determining at least one part of a knowledge graph. A body of text is made available; for one sentence from the body of text, a first, second, and third input respectively for a first, second, and third classifier is determined. Each of the first, second, and third inputs includes a numerical representation of at least one part of the sentence. A numerical representation of a first probability is determined by the first classifier as a function of the first input, which indicates whether or not the sentence relates to the knowledge graph. If the numerical representation of the first probability satisfies a first condition, a numerical representation of a second probability is determined by the second classifier as a function of the second input, which defines a first type for the word from the sentence.

Abstract: An example method is described. The method includes receiving, by a computing system, data indicative of a call into an interactive voice response (IVR) system from a user device and determining, by the computing system and based on the data, a set of actions performed by the user device within the IVR system and a corresponding set of results performed by the IVR system during the call. Additionally, the method includes converting, by the computing system, the set of actions and the corresponding set of results into a sequence of code pairs using a dictionary established based on training data, determining, by the computing system, an activity pattern during the call based on the sequence of code pairs; and calculating, by the computing system, a probability that the call is fraudulent based on the activity pattern during the call.

Abstract: A method for enhancing an audio signal in a full duplex communication system includes the steps of: a) receiving a far end audio signal from a communication input; b) forwarding the far end audio signal to an audio speaker; c) receiving a near end audio signal from a microphone; d) performing an echo reduction on the received near end audio signal; e) forwarding the near end audio signal after the echo reduction to a communication output; f) determining whether a residual echo still exists in the near end audio signal after the echo reduction; and g) attenuating the near end audio signal or deactivating its forwarding to the communication output if the existence of residual echo is determined.

Abstract: Disclosed herein are system, method, and computer program product embodiments for categorizing customer complaints on social media using a model trained on customer voice calls or chats with agents. Additionally, users interested in monitoring regulatory compliance issues based on customer complaints can receive notifications regarding complaints that are linked to regulatory topic areas, without the need to manually scan vast numbers of social media postings.

Abstract: A hypothesis stitcher for speech recognition of long-form audio provides superior performance, such as higher accuracy and reduced computational cost. An example disclosed operation includes: segmenting the audio stream into a plurality of audio segments; identifying a plurality of speakers within each of the plurality of audio segments; performing automatic speech recognition (ASR) on each of the plurality of audio segments to generate a plurality of short-segment hypotheses; merging at least a portion of the short-segment hypotheses into a first merged hypothesis set; inserting stitching symbols into the first merged hypothesis set, the stitching symbols including a window change (WC) symbol; and consolidating, with a network-based hypothesis stitcher, the first merged hypothesis set into a first consolidated hypothesis.

Abstract: In one aspect, a headset assembly may include a headset housing, at least one processor, and a microphone boom coupled to the headset housing. The microphone boom may include an infrared (IR) sensor on a distal end segment, where the IR sensor may be accessible to the at least one processor. The microphone boom may further include at least one microphone accessible to the at least one processor. Additionally, the headset assembly may include storage accessible to the at least one processor. The storage may include instructions executable by the at least one processor to receive input from the IR sensor and, based on the input from the IR sensor, perform mouth feature extraction. The instructions may also be executable to execute at least one function based on the mouth feature extraction.

Abstract: The occurrence cost of unknown words that are not registered in a morphological analysis dictionary is calculated by applying an occurrence cost regression model, which is a learning model. An information processing device includes a notation feature amount extraction unit that extracts a notation feature amount of a character string, a part-of-speech feature amount extraction unit that extracts a part-of-speech feature amount of the character string, and an occurrence cost estimation unit that receives the notation feature amount and the part-of-speech feature amount and calculates an occurrence cost of the character string by applying an occurrence cost regression model. The occurrence cost regression model is a learning model that estimates the occurrence cost from the notation feature amount and the part-of-speech feature amount of a character string, generated by a learning process using registration data of an existing morphological analysis dictionary as teacher data.

Abstract: A safety system for supervision of a child involving interaction between a pre-trained first adult conveying responsibility for supervision of the child to a pre-trained second adult. The system utilizes a specific interactive scripted conversation between the first adult and the second adult to assign responsibility for supervision of the child to the second adult. Following this, the first adult transfers a wearable to the second adult to provide a visual and tactile transfer of the responsibility of supervision of the child from the first adult and acceptance of the responsibility of supervision of the child by the second adult corresponding to the interactive conversation between the first adult and the second adult.

Abstract: A pharmacy management system includes a processor and a memory storing instructions that, when executed by processor, cause the pharmacy management system to train a machine learning model; receive a sig code utterance; analyze the sig code utterance using the trained machine learning model; and generate an output. A computer-implemented method includes training a machine learning model; receiving a sig code utterance; analyzing the sig code utterance using the trained machine learning model; and generating an output. A non-transitory computer readable medium includes program instructions that when executed, cause a computer to train a machine learning model; receive a sig code utterance; analyze the sig code utterance using the trained machine learning model; and generate an output.

Abstract: Some implementations relate to methods, systems, and computer-readable media to generate text tags for games. In some implementations, a computer-implemented method to generate one or more text tags includes obtaining a plurality of chat transcripts, each chat transcript associated with a respective gameplay session of a respective game of a plurality of games. Each chat transcript includes content provided by participants in the gameplay session. The method further includes programmatically analyzing the plurality of chat transcripts to determine one or more characteristics for each game of the plurality of games, and generating a text tag for at least one game of the plurality of games based on the one or more characteristics of the at least one game.

Abstract: An embedded sensor can include an audio detector, a digital signal processor, a library, and a rules engine. The digital signal processor can be configured to receive signals from the audio detector and to identify the environment in which the embedded sensor is located. The library can store statistical models associated with specific environments, and the digital signal processor can be configured identify specific events based on detected sounds within the particular environment by utilizing the statistical model associated with the particular environment. The DSP can associate a probability of accuracy for the identified audible event. A rules engine can be configured to receive the probability and transmit a report of the detected audible event.

Abstract: Audio objects are associated with positional metadata. A received downmix signal comprises downmix channels that are linear combinations of one or more audio objects and are associated with respective positional locators. In a first aspect, the downmix signal, the positional metadata and frequency-dependent object gains are received. An audio object is reconstructed by applying the object gain to an upmix of the downmix signal in accordance with coefficients based on the positional metadata and the positional locators. In a second aspect, audio objects have been encoded together with at least one bed channel positioned at a positional locator of a corresponding downmix channel. The decoding system receives the downmix signal and the positional metadata of the audio objects. A bed channel is reconstructed by suppressing the content representing audio objects from the corresponding downmix channel on the basis of the positional locator of the corresponding downmix channel.

Abstract: An electronic device according to various embodiments, may include a speaker, a temperature sensor disposed in at least some area inside the speaker, and at least one processor configured to obtain a first temperature of the at least some area using the temperature sensor, obtain a second temperature based on measuring impedance of a voice coil included in the speaker, determine a temperature of the speaker based on at least one of the first temperature and the second temperature, and change a function of the electronic device based at least on the determined temperature of the speaker.

Abstract: An apparatus is described, the apparatus including a case, a display assembly, a chassis connected to the display assembly, a suspension component between the display assembly and the case, wherein the suspension component is configured to allow the display assembly to move relative to the case, at least one vibrating element configured to actuate the chassis to move the display assembly relative to the case to generate at least one of acoustic waves or haptic/tactile effect, and an internal cavity below the display, wherein electronic components of the apparatus are located at the internal cavity.

Abstract: An earpiece with structure for positioning and retaining the earpiece and with structure for sealing against the entrance to the ear canal to provide passive noise attenuation. The positioning and retaining structure engages features of the lateral surface of the ear. The structure for sealing against the entrance to the ear canal includes a conical structure.

Abstract: At a first layer of an echo canceler, a first compensation for a first set of properties of output of an audio capture device of a first communication environment is applied. The first set of properties includes a property resulting from a difference in clock speeds of an audio capture device and an audio rendering device of the first communication environment. At a second layer of the echo canceler, at which output of the first layer is received, a second compensation for a second set of properties of the output of the first layer is applied. The second set of properties includes an echo. Applying the compensations comprises modifying neural network weights. Output of the second layer is transmitted to a second communication environment.

Abstract: The present invention addresses the problem of providing a technique for assisting the realization of more efficient business activities, while taking account of objective indicators. In a server 1 which supports a user U having a telephone call with a call destination C, an acquiring unit 101 acquires information recorded during the call between the user U and the call destination C, as call information. An extracting unit 102 detects utterance segments VS1 to VSn in which speech is present, from the acquired call information, and extracts speech information VI1 to VIm from each utterance segment VS1 to VSn. An analyzing unit 103 performs analysis based on elements E1 to Ep, on the basis of the extracted speech information VI1 to VIm. A generating unit 104 generates business support information for supporting the call with the user U, on the basis of the results of the analysis. A presenting unit 105 presents the generated business support information to the user U.