Abstract: A wearable device providing an augmented reality experience for the benefit of hearing impaired persons is disclosed. The augmented reality experience displays a virtual text caption box that includes text that has been translated from speech detected from surrounding speakers.

Abstract: The present technology reduces a process load in a reception side when a plurality of types of audi data is transmitted. A metafile having meta information used to acquire, in a reception device, a predetermined number of audio streams including a plurality of groups of encoded data is transmitted. To the metafile, attribute information indicating each attribute of the encoded data of the plurality of groups is inserted. For example, to the metafile, stream correspondence relation information indicating in which audio stream the encoded data of the plurality of groups is included respectively is further inserted.

Abstract: Disclosed are a packet loss concealment method and apparatus a using a generative adversarial network. A method for packet loss concealment in voice communication may include training a classification model based on a generative adversarial network (GAN) with respect to a voice signal including a plurality of frames, training a generative model having a contention relation with the classification model based on the GAN, estimating lost packet information based on the trained generative model with respect to the voice signal encoded by a codec, and restoring a lost packet based on the estimated packet information.

Abstract: In order to detect a replay attack in a speaker recognition system, at least one feature is identified in a detected magnetic field. It is then determined whether the at least one identified feature of the detected magnetic field is indicative of playback of speech through a loudspeaker. If so, it is determined that a replay attack may have taken place.

Abstract: There is provided an information processing device, an information processing method, and a program which are capable of performing voice recognition adaptively to the degree of excitement in the sound collection state. The information processing device includes: an acquiring unit configured to acquire information indicating a degree of excitement in a collection state of a voice; and a voice recognizing unit configured to perform first voice recognition based on a phoneme of the voice on the basis of the information indicating the degree of excitement.

Abstract: Embodiments of the invention are directed to systems and methods for biometrics transaction processing. A location of a device associated with a user may be determined. A reference to a biometric data model associated with the user stored within a database may be retrieved, based at least in part on the location. Biometric data may be received from the user. Using the reference, the biometric data may be compared to the biometric data model stored within the database. A determination may be made whether the user is authenticated for the transaction based on the comparing step.

Abstract: Various embodiments of the invention provide methods, systems, and computer program products for conducting analytics on a communication so that search terms and corresponding synonyms can be considered in a context. A user identifies search terms and synonyms for the terms are provided. The user selects one or more of the synonyms and a topic model is applied to the search terms and selected synonyms to identify topics. The user selects a topic and communications associated with the topic are identified. The words articulated during the communications are then analyzed to identify occurrences where the search terms and synonyms were articulated during the communications. A GUI is displayed representing one of the communications with a plurality of icons, each icon representing one of the occurrences. Accordingly, the user may select a particular icon and a portion of the communication containing the corresponding occurrence is played and/or displayed for the user.

Abstract: A Chinese common sense comprehension system includes a simulation module for simulating the Cangjie codes into concept information and an integration module for integrating the concept information into target information. Therefore, the Chinese common sense comprehension system adopts an innovative logical way of learning Chinese, thereby improving the accuracy of the artificial intelligence device to understand Chinese.

Abstract: The present application provides a voice processing method, an apparatus, a device, and a storage medium, including: acquiring a first acoustic feature of each of N voice frames, where N is a positive integer greater than 1; applying a neural network algorithm to N first acoustic features to obtain a first mask; modifying the first mask according to VAD information of the N voice frames to obtain a second mask; and processing the N first acoustic features according to the second mask to obtain a second acoustic feature, resulting in more effective noise suppression and a lower damage to the voice.

Abstract: Representative embodiments disclose mechanisms to separate and recognize multiple audio sources (e.g., picking out individual speakers) in an environment where they overlap and interfere with each other. The architecture uses a microphone array to spatially separate out the audio signals. The spatially filtered signals are then input into a plurality of separators, so each signal is input into a corresponding signal. The separators use neural networks to separate out audio sources. The separators typically produce multiple output signals for the single input signals. A post selection processor then assesses the separator outputs to pick the signals with the highest quality output. These signals can be used in a variety of systems such as speech recognition, meeting transcription and enhancement, hearing aids, music information retrieval, speech enhancement and so forth.

Abstract: Embodiments of the present invention disclose a method, a computer program product, and a computer system for a naming convention reconciler. A computer receives and pre-processing first dictionary 114 and second dictionary 116. In addition, the computer parses the pre-processed dictionaries to extract one or more names from each of the two dictionaries. The computer then generates a hash table of the names extracted from the second dictionary and searches the hash table for names that include a word in common with a name extracted from first dictionary 114. Based on identifying a name in the hash table that includes a word in common with a name extracted from first dictionary 114, the computer determines a similarity between the names and stores an association between the names having a greatest similarity.

Abstract: Systems and methods are described to address shortcomings in conventional systems by correcting an erroneous term in on-screen caption text for a media asset. In some aspects, the systems and methods identify the erroneous term in a text segment of the on-screen caption text, and identify one or more video frames of the media asset corresponding to the text segment. The systems and methods further identify a contextual term related to the erroneous term from the one or more video frames. By accessing a knowledge graph, the systems and methods identify a candidate correction based on the contextual term and a portion of the text segment. Lastly, the systems and methods replaces the erroneous term with the candidate correction.

Abstract: One embodiment provides a method, including: receiving an input from a first user requesting information; generating a conversation model from a dialog that occurs between the user and a human agent; recording the human agent performing an external action required to respond to the input; mapping steps performed during performance of the external action to conversation slots within the dialog; generating an integrated interpretable conversation model comprising a dialog and action script; receiving, at a conversational agent system, a subsequent input from a second user requesting similar information to the information requested by the first user; and providing, by the conversational agent system, a response to the subsequent input, wherein the providing a response comprises the conversational agent system utilizing the integrated interpretable conversational model to replay (i) the dialog and (ii) the action script using the subsequent input.

Abstract: The present disclosure provides a speech synthesis method and apparatus, a computer device and a readable medium. The method comprises: when problematic speech appears in speech splicing and synthesis, predicting a time length of a state of each phoneme corresponding to a target text corresponding to the problematic speech and a base frequency of each frame, according to pre-trained time length predicting model and base frequency predicting model; according to the time length of the state of each phoneme corresponding to the target text and the base frequency of each frame, using a pre-trained speech synthesis model to synthesize speech corresponding to the target text; wherein the time length predicting model, the base frequency predicting model and the speech synthesis model are all obtained by training based on a speech library resulting from speech splicing and synthesis.

Abstract: Techniques for implementing multiple wakeword detectors on a single device are described. A digital signal processor (DSP) of the device may initially include an untrained wakeword detection component. The wakeword detection component of the DSP may be trained by engaging a user to speak particular utterances. Once a companion application is configured to implement a wakeword detection component, the companion application's wakeword detection component may be trained specific to the user of the device. Once the companion application's wakeword detection component is trained, the DSP wakeword detection component may be deactivated or its accuracy adjusted.

Abstract: A decoder is provided. The decoder includes a parametric decoding unit for generating a plurality of first estimated audio object signals by upmixing three or more downmix signals, wherein the three or more downmix signals encode a plurality of original audio object signals, wherein the parametric decoding unit is configured to upmix the three or more downmix signals depending on parametric side information indicating information on the plurality of original audio object signals. Moreover, the decoder includes a residual processing unit for generating a plurality of second estimated audio object signals by modifying one or more of the first estimated audio object signals, wherein the residual processing unit is configured to modify the one or more of the first estimated audio object signals depending on one or more residual signals.

Abstract: Techniques are described for fulfilling an utterance request for an item represented within a video rendered at a client device. In some implementations, a user account associated with the request is identified, enabling a video stream transmitted in association with the user account at the time that the request was uttered to be identified. In one technique, a timestamp associated with the request is used to identify the relevant portion of the video stream. The item represented within the portion of the video stream can be identified using various techniques and/or information such as image recognition, metadata within the video, subtitles, closed captions, and/or a database mapping between the item and a video content item transmitted in the video stream.

Abstract: Disclosed are a method and an apparatus for high frequency decoding for bandwidth extension. The method for high frequency decoding for bandwidth extension comprises the steps of: decoding an excitation class; transforming a decoded low frequency spectrum on the basis of the excitation class; and generating a high frequency excitation spectrum on the basis of the transformed low frequency spectrum. The method and apparatus for high frequency decoding for bandwidth extension according to an embodiment can transform a restored low frequency spectrum and generate a high frequency excitation spectrum, thereby improving the restored sound quality without an excessive increase in complexity.

Abstract: This disclosure describes systems and methods for using a primary device, communicatively coupled to a remote system, to configure or re-configure a secondary device in the same environment as the primary device. In some instances, the primary device may communicatively couple to the secondary device via a short-range wireless connection and to the remote system via a wireless area network (WAN), a wired connection, or the like. Thus, the primary device may act as an intermediary between the secondary device and the remote system for configuring the secondary device.

Abstract: A chatbot-based cloud management system, including: an interface for receiving a query from a client through a plurality of access channels, and delivering a response generated in response to the received query to the client; a chatbot engine for performing a response processing to the query based on a chat learning model learned in advance and a chat knowledge context, and outputting event occurrence information when a request event from the query occurs; and a processing engine for confirming failure occurrence situation of an infra where the request event has occurred and providing it to the chatbot engine by generating failure countermeasures corresponding to the failure occurrence situation based on a failure model learned in advance and a failure processing rule, when event occurrence information is received from the chatbot engine.