Abstract: Performing an operation comprising analyzing an electronic text corpus by a natural language processing (NLP) algorithm executing on a processor to determine a set of target terms specified in the electronic text corpus, analyzing the electronic text corpus by the NLP algorithm to determine a weight for each pair of terms in the set of target terms, and storing an indication of each pair of terms and the respective weight in a lookup table in a computer memory for runtime analysis of an input text data.

Abstract: A method for producing a multi-channel audio signal from one or more sound object signals is disclosed, where, for each sound object signal a plurality of width signals is produced, the amplitudes of the width signals following a substantially Gaussian distribution. The width signals are processed to produce a plurality of pan signals which are mapped to at least one channel. Each channel in the audio signal is produced by combining the pan signals from each sound object. An apparatus for reproducing such a multi-channel audio signal is also disclosed, in which a plurality of first loudspeakers are provided spaced around a first arc forward of a predetermined listening zone, each of the first loudspeakers facing towards the listening zone and substantially equidistant therefrom. A plurality of second loudspeakers are provided spaced around a second arc behind the listening zone, each of the second loudspeakers facing towards the listening zone.

Abstract: A translation device is configured to translate from a first language into a second language and includes a first language acquisition unit, a polyseme processor, and a first language output unit. The first language acquisition unit acquires a sentence in the first language. The polyseme processor determines whether or not a word in the second language for a word in the first language included in the sentence is a polyseme, and acquires a plurality of candidate meanings for the word in the second language when the word in the second language is determined as a polyseme. The first language output unit outputs the plurality of candidate meanings.

Abstract: Systems are provided to facilitate continuous detection of words, names, phrases, or other sounds of interest and, responsive to such detection, provide a related user experience. The user experience can include providing links to media, web searches, translation services, journaling applications, or other resources based on detected ambient speech or other sounds. To preserve the privacy of those using and/or proximate to such systems, the system refrains from transmitting any information related to the detected sound unless the system receives permission from a user. Such permission can include the user interacting with a provided web search link, media link, or other user interface element.

Abstract: Provided is a method for beamforming by using maximum likelihood estimation in a speech recognition apparatus, including: (a) receiving an input signal (Xn,k) at a time frame n and a frequency k where noise is mixed: (b) determining a probability density function for a target signal (Yn,k) obtained by removing the noise from the input signal satisfies a complex generalized Guassian distribution or a complex gamma distribution where an average value is zero in a time-frequency domain; (c) estimating a variance (?n,k) of the target signal so as to maximize log likelihood for the probability density function; (d) estimating a filter (wk) maximizing a cost function so as to maximize the log likelihood for the probability density function; and (e) repeatedly performing the estimation of the steps (c) and (d) until the filter (wk) coverages, and finally acquiring a final filter (wk).

Abstract: Method, system, and apparatus for storing conversation data of a conversation onto a blockchain network, the conversation data comprising terms of an agreement, the method comprising: receiving audio data of a conversation between two or more participants; creating a transcript of at least some of the audio data; accessing a database comprising a plurality of words or phrases. The method, system, and apparatus are also for obtaining, from the database, predefined one or more words associated with a predefined topic; searching the transcript for the predefined one or more words; filtering the transcript based on the predefined one or more words; and storing the conversation data onto a first block of a blockchain stored on the blockchain network, wherein the conversation data comprises the filtered transcript.

Abstract: Methods, systems, and computer readable media can be operable to facilitate controlled caching of text-to-speech data. When text is identified for a text-to-speech conversion, a duration value to be associated with the text may be determined, and the identified text and duration value may be included within a request for a conversion of the text. An intermediate server may retrieve a speech file that is generated in response to the conversion request, and the intermediate server may cache the speech file for a certain period of time that is indicated by the duration value.

Abstract: Described herein is an AI voice response system configured to and methods, computer-readable media, techniques, and methodologies for relaying a voice command received from a user unknown to the AI voice response system to another AI voice response system capable of identifying the user and executing the voice command. An execution result of executing the voice command is then sent back to the AI voice response system that received the voice command for presentation to the user.

Abstract: Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: activating a streaming media recording buffer that records streaming media of an online conference, the online conference having first second and third user online conference participant users; examining data to return an action decision, the examining data to return an action decision including examining data of the streaming media recording buffer to identify an anomalous sound represented in the recorded media stream data of the streaming media recording buffer; returning an action decision based on the examining data to return an action decision, the action decision being an action to mitigate the anomalous sound; and providing one or more output to mitigate the anomalous sound in accordance with the returned action decision.

Abstract: Aspects of the disclosure relate to enhanced dynamic training response output generation control systems with enhanced dynamic training response output determinations. A computing platform may receive, from the user device and in response to an initial dynamic training interface, a training request input. The computing platform may send, to an NLU engine, the training request input and commands directing the NLU engine to perform natural language understanding and processing on the training request input to determine a natural language result output. Using the natural language result output, the computing platform may determine third party data sources that correspond to the natural language result output, and may request source data from the third party data sources. Using the source data and the natural language result output, the computing platform may generate a dynamic training response output, and may direct the user device to cause display of the dynamic training response output.

Abstract: Headphones are provided having virtual controls displayed on a circular touch screen and integrated memory, the headphones comprising a arcuate headband, a receiver, a transmitter, and computer-readable memory. The headphones are adapted to interact with a wearer through the virtual controls, permitting a wearer to share media wirelessly, assign playback settings, and to accept wireless input from a remote data processing (DPD) device. The headphones may perform a hearing screen test to determine using tones at predetermined frequencies then to amplify frequencies at which a user experiences hearing loss during playback.

Abstract: An audio control system of an electromagnetic cradle includes an audio transmitting and receiving unit, a cloud server, and a function execution unit. The audio transmitting and receiving unit receives an audio command emitted from a user. The cloud server is connected with the audio transmitting and receiving unit through a network. The cloud server identifies and compares the audio command of the audio transmitting and receiving unit. The function execution unit is connected with the cloud server through the network. The function control module is driven by function indication of the cloud server to execute related functions, including playing the music, lighting or shaking the cradle.

Abstract: Techniques for improving the accuracy, relevancy, and efficiency of a computer system of an online service by providing a user interface to optimize a digital page of a user on the online service are disclosed herein. In some embodiments, a computer system receives a plurality of phrases, and then, for each one of the plurality of phrases, selects a corresponding section of a page of a first user to suggest for placement of the phrase from amongst a plurality of sections using a placement classifier, and generates a corresponding recommendation for the page of a first user based on the phrase and the determined corresponding section of the page of the first user, with the recommendation comprising a suggested addition of the phrase to the determined corresponding section of the page of the first user.

Abstract: A method for separating and authenticating speech of a speaker on an audio stream of speakers over an audio channel may include receiving audio stream data of the audio stream with speech from a speaker to be authenticated speaking with a second speaker. A voiceprint may be generated for each data chunk in the audio stream data divided into a plurality of data chunks. The voiceprint for each data chunk may be assessed as to whether the voiceprint has speech belonging to the speaker to be authenticated or to the second speaker using representative voiceprints of both speakers. An accumulated voiceprint may be generated using the verified data chunks with speech of the speaker to be authenticated. The accumulated voiceprint may be compared to the reference voiceprint of the speaker to be authenticated for authenticating the speaker speaking with the second speaker over the audio channel.

Abstract: A method includes receiving, at an audio encoder, multiple streams of audio data, where N is the number of the received multi streams. The method includes determining a similarity value for each stream of the multiple streams and comparing the similarity value for each stream of the multiple streams with a threshold. The method also includes identifying, based on the comparison, L (L<N) number of streams to be encoded among the N number of the multiple streams. The method includes encoding the identified L number of streams to generate an encoded bitstream.

Abstract: A method comprises converting an audio frequency domain signal into one or more voltage signals. Then the characteristics of the one or more voltage signals are determined. Afterwards the characteristics of the one or more voltage signals are compared with one or more characteristics of an audio trigger command. Activation of an audio user interface is then activated on the basis of the comparison.

Abstract: According to the present disclosure, a sound output device includes: a sound acquisition part configured to acquire sound to be output to the other end of a sound guide part, one end of which is arranged near an entrance of an ear canal of a listener, the sound guide part having a hollow structure; and a head-related transfer function adjustment part configured to adjust a head-related transfer function of sound captured by the sound guide part. Since the head-related transfer function adjustment part adjusts the head-related transfer function of sound captured by the sound guide part, it is possible to listen to both ambient sound and sound provided from a sound output device such that the listener does not feel strangeness even in the state in which the listener is wearing the sound output device.

Abstract: An electronic device and method are provided for processing user speech.

Abstract: Systems and methods that access an online networked resource using a locator are disclosed. A first item of content on the networked resource is identified. A trigger rule comprising keywords and a sentiment classifier is accessed. A neural network, including input, hidden, and output layers, is used to assign a sentiment classification to the first item of content. The trigger rule, the sentiment classification, and identified keywords, are used to determine whether response content is to be posted to the online networked resource. In response to determining, using the trigger rule, the assigned sentiment classification, and keywords identified in the first item of content, that response content is to be posted to the online networked resource, the sentiment classification and identified keywords are used to select and/or generate a second item of content, and the second item of content is enabled to be posted to the online networked resource.

Abstract: In one embodiment, a method includes receiving, from a client system associated with a first user, a first user input by the first user, wherein the first user input is associated with a current dialog session, identifying a first language register associated with the first user based on the first user input, accessing a plurality of language-register models associated with a plurality of language registers stored in a data store, selecting a first language-register model from the plurality of language-register models based on the identified first language register, and generating a first communication content responsive to the first user input, the first communication content being personalized for the first user based on the selected first language-register model.