Abstract: A voice signal conversion model learning device includes: a generation unit configured to execute generation processing of generating a conversion destination voice signal on the basis of an input voice signal that is a voice signal of an input voice, conversion source attribute information that is information indicating an attribute of an input voice that is a voice represented by the input voice signal, and conversion destination attribute information indicating an attribute of a voice represented by the conversion destination voice signal that is a voice signal of a conversion destination of the input voice signal; and an identification unit configured to execute voice estimation processing of estimating whether or not a voice signal that is a processing target is a voice signal representing a vocal sound actually uttered by a person on the basis of the conversion source attribute information and the conversion destination attribute intonation, wherein the conversion destination voice signal is input to th

Abstract: A digital assistant function is provided to individual users even when a primary device having the digital assistant function is at a location away from a hand of a user. An information processing device that relays sound data to a primary device that executes a digital assistant process includes: a sound acquiring unit that acquires surrounding sounds as sound data; a destination device determination unit that determines a destination primary device which is the primary device that is a destination of the sound data; a transmitting and receiving unit that transmits the sound data to the destination primary device and receives, from the destination primary device, a result of a digital assistant process executed depending on the sound data as a reply; and a reply presentation unit that presents the reply received at the transmitting and receiving unit.

Abstract: Natural language generation technology is disclosed that applies artificial intelligence to structured data to determine content for expression in natural language narratives that describe the structured data. A graph data structure is employed, where the graph data structure comprises a plurality of nodes. Each of a plurality of the nodes (1) represents a corresponding intent so that a plurality of different nodes represent different corresponding intents and (2) is associated with one or more links to one or more of the nodes to define relationships among the intents.

Abstract: Prevention of voice misappropriation in voice interaction/response systems. The system relies on telemetry data, including thermal data of components to determine whether a received voice command was made by actual voice. If the voice command is determined to have been made by an actual voice, a response to the command is generated and transmitted, otherwise if the voice command is determined to have likely not been made by an actual voice (e.g., artificial means replicating a voice, such as a laser or the like), no response to the command is transmitted or action taken with respect to the command.

Abstract: Example methods and systems are directed to generating knowledge graph entities from text. Natural language text is received as input and processed using named entity recognition (NER), part of speech (POS) recognition, and business object recognition (BOR). The outputs of the NER, POS, and BOR processes are combined to generate knowledge entity triples comprising two entities and a relationship between them. Keywords are extracted from the text using NER to generate a set of entities. A node in a knowledge graph is created for at least some of the entities. A POS tagger identifies verbs in the text, generating a set of verbs. Relational verbs (e.g., “talk to” or “communicated with”) are detected and used to create edges in the knowledge graph. The knowledge graph may be converted back to natural language text using a trained machine learning model.

Abstract: Systems and methods are provided herein for responding to a voice command at a volume level based on a volume level of the voice command. For example, a media guidance application may detect, through a first voice-operated user device of a plurality of voice-operated user devices, a voice command spoken by a user. The media guidance application may determine a first volume level of the voice command. Based on the volume level of the voice command, the media guidance application may determine that a second voice-operated user device of the plurality of voice-operated user devices is closer to the user than any of the other voice-operated user devices. The media guidance application may generate an audible response, through the second voice-operated user device, at a second volume level that is set based on the first volume level of the voice command.

Abstract: The techniques disclosed herein provide intelligent display of auditory world experiences. Specialized AI models are configured to display integrated visualizations for different aspects of the auditory signals that may be communicated during an event, such as a meeting, chat session, etc. For instance, a system can use a sentiment recognition model to identify specific characteristics of a speech input, such as volume or tone, provided by a participant. The system can also use a speech recognition model to identify keywords that can be used to distinguish portions of a transcript that are displayed. The system can also utilize an audio recognition model that is configured to analyze non-speech audio sounds for the purposes of identifying non-speech events. The system can then integrate the user interface attributes, distinguished portions of the transcript, and visual indicators describing the non-speech events.

Abstract: Systems and methods for optimizing voice detection via a network microphone device are disclosed herein. In one example, individual microphones of a network microphone device detect sound. The sound data is captured in a first buffer and analyzed to detect a trigger event. Metadata associated with the sound data is captured in a second buffer and provided to at least one network device to determine at least one characteristic of the detected sound based on the metadata. The network device provides a response that includes an instruction, based on the determined characteristic, to modify at least one performance parameter of the NMD. The NMD then modifies the at least one performance parameter based on the instruction.

Abstract: Methods and systems for correction of a likely erroneous word in a speech transcription are disclosed. By evaluating token confidence scores of individual words or phrases, the automatic speech recognition system can replace a low-confidence score word with a substitute word or phrase. Among various approaches, neural network models can be used to generate individual confidence scores. Such word substitution can enable the speech recognition system to automatically detect and correct likely errors in transcription. Furthermore, the system can indicate the token confidence scores on a graphic user interface for labeling and dictionary enhancement.

Abstract: A method for modifying a voice-signal transcription generated by an automatic speech recognition engine from a voice signal, prior to a generation of a response by a semantic engine equipped with at least one ontology comprising a vocabulary space, from an injection of a question, comprises the following steps: determining the set of all of the words of the transcription not belonging to the space, and for each word of the determined set: a step of word-embedding of the word in the space; determining semantic distances between the embedding and each of the words of the space; a step of selecting at least one word of the space; and modifying the transcription by replacing the word of the transcription with at least one selected word in order to generate a modified signal transcription.

Abstract: Conventional audio compression technologies perform a standardized signal transformation, independent of the type of the content. Multi-channel signals are decomposed into their signal components, subsequently quantized and encoded. This is disadvantageous due to lack of knowledge on the characteristics of scene composition, especially for e.g. multi-channel audio or Higher-Order Ambisonics (HOA) content. A method for decoding an encoded bitstream of multi-channel audio data and associated metadata is provided, including transforming the first Ambisonics format of the multi-channel audio data to a second Ambisonics format representation of the multi-channel audio data, wherein the transforming maps the first Ambisonics format of the multi-channel audio data into the second Ambisonics format representation of the multi-channel audio data.

Abstract: A facility for representing a mandate occurring in an authority document with a control is described. For each of one or more controls in a set of existing controls, the facility determines a similarity score measuring the similarity of the mandate and the control; where the similarity score exceeds a similarity threshold, the facility links the mandate to the control. Where the mandate is not linked to any control in the set of controls, the facility adds a control to the set of controls that is based on the mandate, and links the mandate to the added control.

Abstract: Encoding and decoding systems are described for the provision of high quality digital representations of audio signals with particular attention to the correct perceptual rendering of fast transients at modest sample rates. This is achieved by optimising downsampling and upsampling filters to minimise the length of the impulse response while adequately attenuating alias products that have been found perceptually harmful.

Abstract: Systems and methods for determining whether a first electronic device detects a media item that is to be output by a second electronic device is described herein. In some embodiments, an individual may request, using a first electronic device, that a media item be played on a second electronic device. The backend system may send first audio data representing a first response to the first electronic device, along with instructions to delay outputting the first response, as well as to continue sending audio data of additional audio captured thereby. The backend system may also send second audio data representing a second response to the second electronic device along with the media item. Text data may be generated representing the captured audio, which may then be compared with text data representing the second response to determine whether or not they match.

Abstract: A non-transitory computer-readable recording medium stores a program for causing a computer to execute a process, the process includes acquiring training data that includes a first sentence expressed in a first language and a second sentence expressed in a second language, identifying a named entity and parts of speech from the first sentence, and generating, based on the training data, a translation model that includes an attention mechanism for the named entity and the parts of speech.

Abstract: One or more associated identifiers are determined based on one or more associated tag types of an interactable element of web content. The determined one or more associated identifiers are associated with the interactable element. Based on the association of the determined one or more associated identifiers with the interactable element, one of the interactable element is matched to a received speech input. An action is performed with respect to the interactable element based on the matching.

Abstract: A voice information processing apparatus sequentially converts an utterance of a user into text during a voice reception period that is a period in which an uttered voice to be converted into text is received from a user, and in a case where it can be regarded that the utterance of the user has been interrupted, the voice information processing apparatus automatically causes utterance content already uttered by the user to be output by a voice during the voice reception period. As a result, the voice information processing apparatus can cause the user to recognize a content of a sentence that has been uttered by the user so far and converted into text, when it can be regarded that the utterance of the user has been interrupted.

Abstract: Artificial intelligence-based processing can be used to classify audio information received from an audio input unit. In an example, audio information can be received from a microphone configured to monitor an environment. A processor circuit can identify identifying one or more features of the audio information received from the microphone and use a first applied machine learning algorithm to analyze the one or more features and determine whether the audio information includes an indication of an abnormal event in the environment. In an example, the processor circuit can use a different second applied machine learning algorithm, such as a neural network-based deep learning algorithm, to analyze the same one or more features and classify the audio information as including an indication of a particular event type in the environment.

Abstract: In one embodiment, a method includes accessing a decoded hypothesis corresponding to an utterance, computing a predicted probability of observing each token in the decoded hypothesis by having a local first machine-learning model process the decoded hypothesis, computing a confidence score for each token in the decoded hypothesis by having a second machine-learning model process the decoded hypothesis, where the confidence score indicates a degree of confidence for the token to be observed at its position, calculating a loss for the computed predicted probabilities of observing tokens in the decoded hypothesis based on the computed confidence scores, and updating parameters of the local first machine-learning model based on the calculated loss.

Abstract: Techniques are described herein for warm word arbitration between automated assistant devices. A method includes: determining that warm word arbitration is to be initiated between a first assistant device and one or more additional assistant devices, including a second assistant device; broadcasting, by the first assistant device, to the one or more additional assistant devices, an active set of warm words for the first assistant device; for each of the one or more additional assistant devices, receiving, from the additional assistant device, an active set of warm words for the additional assistant device; identifying a matching warm word included in the active set of warm words for the first assistant device and included in the active set of warm words for the second assistant device; and enabling or disabling detection of the matching warm word by the first assistant device, in response to identifying the matching warm word.