Abstract: Methods and systems for voice-based identification of related products/services are provided. Exemplary systems may include a wireless communication-based tag reader that polls for a wireless transmission-based tag and reads information associated with the wireless transmission-based tag and a processor that executes instructions to identify a product/service associated with the wireless transmission-based tag, identify a plurality of products/services stored in a product/service database identified as related to the product/service associated with the wireless transmission-based tag based on a trend related to prior purchases to identify a related product/service, and generate a voice-based utterance based on the identified set of one or more related products/services.

Abstract: Example techniques involve systems with multiple acoustic echo cancellers. An example implementation captures first audio within an acoustic environment and detecting, within the captured first audio content, a wake-word. In response to the wake-word and before playing an acknowledgement tone, the implementation activates (a) a first sound canceller when one or more speakers are playing back audio content or (b) a second sound canceller when the one or more speakers are idle. In response to the wake-word and after activating either (a) the first sound canceller or (b) the second sound canceller, the implementation outputs the acknowledgement tone via the one or more speakers. The implementation captures second audio within the acoustic environment and cancelling the acoustic echo of the acknowledgement tone from the captured second audio using the activated sound canceller.

Abstract: Extracting data from documents is challenging due to the variation in structure, content, styles across geographies and functional areas. Further complex relation types are characterized by one or more of N-ary entity mention arguments, cross sentence span of entity mentions for a relation mention, missing entity mention arguments and entity mention arguments being multi-valued. The present disclosure addresses these gaps in the art to extract entity mentions and relation mentions using a joint neural network model including two sequence labelling layers which are trained jointly. The mentions are extracted from documents to facilitate downstream processing. A first RNN layer creates sentence embeddings for each sentence in the document being processed and predicts entity mentions. A second RNN layer predicts labels for each sentence span corresponding to a relation type.

Abstract: A system for generating videos uses a domain-specific instructional language and a video rendering engine that produces videos against a digital product which changes and evolves over time. The video rendering engine uses the instructions in an instruction markup document written in the domain-specific instructional language to generate a video while navigating a web-based document, (which is different from the instruction markup document), representing the digital product for which the video is generated. The video rendering engine navigates the web-based document, coupled with the instruction markup document, which explains the operations to be performed on the web-based document. The instruction markup document also identifies the special effects that manipulate the underlying product in real-time, includes the spoken text for generating subtitles, and provides formalized change management by design.

Abstract: Techniques for improving systems for tracking data access are provided. A system for accessing and encoding data may, upon receiving a request for data, determine whether the data needs to be encoded for the purpose of tracking access to the data. If the system determines that the data needs to be encoded, the system may further determine the information which is to be encoded into the data, such as a client ID/user ID, timestamp, etc. The system may further determine an encoding scheme for the data such as a least significant bit algorithm. The system may further determine encoding data based on the encoding scheme and the information which is to be encoded into the data. The system may also encode the encoding data into the data based on the encoding scheme.

Abstract: A method includes: a bidirectional translation model to be trained and training data are acquired, the training data including a source corpus and a target corpus corresponding to the source corpus; the bidirectional translation model is trained for N cycles, each cycle of training including a forward translation process of translating the source corpus into a pseudo target corpus and a reverse translation process of translating the pseudo target corpus into a pseudo source corpus and N being a positive integer greater than 1; a forward translation similarity and a reverse translation similarity are acquired; and when a sum of the forward translation similarity and the reverse translation similarity converges, it is determined that training of the bidirectional translation model is completed, where the training completed bidirectional translation model is used to perform translating.

Abstract: A secure audio switch comprising: a plurality of host computer interfaces, each for interfacing the secure audio switch with a corresponding host computer, for receiving audio signals from said corresponding host computer; a user audio interface, for interfacing the secure audio switch with at least one user audio device, wherein said at least one user audio device comprises at least one of a speaker or an earphone; an Audio Output Channel (AOC), coupled to said user audio interface comprises audio security device to reduce data leak by intentionally reducing data rate capable of flowing through said AOC to a maximum rate comparable to the minimal rate required for reproducing human speech, and forcing audio data flow only in the direction to said user audio interface by using an analog audio diode and an analog low pass filter in the audio output channel (AOC).

Abstract: A method, apparatus, device, and storage medium for entity linking is disclosed. The method includes: acquiring a target text; determining at least one entity mention included in the target text; determining a candidate entity corresponding to each of the entity mention based on a preset knowledge base; determining a reference text of each of the candidate entity and determining additional feature information of each of the candidate entity; and determining an entity linking result based on the target text, each of the reference text, and each piece of the additional feature information, wherein determining the entity linking result includes determining a probability of linking each of the candidate entity to the entity mention based on a splicing of a first embedding vector and a second embedding vector of the target text and a splicing of a first embedding vector and a second embedding vector of each respective reference text.

Abstract: The LIDAR system includes a first transform component configured to perform a complex mathematical transform on first signals. The LIDAR system also includes a second transform component configured to perform a real mathematical transform on second signals. Electronics are configured to use an output of the first transform component in combination with an output of the second transformation component to generate LIDAR data. The electronics are further configured to use a peak in the output of the first transform component to identify the peak in the output of the second transform component that is located at the beat frequency of the second signals.

Abstract: Systems and methods for increasing the impact of a message for a target individual are provided. An audio recording of the message and audio recordings of the target individual are each associated with transcribed text, which is separated into morphemes. Morphemes in the message are substituted with, or supplemented by, matching morphemes in the audio recordings of the target individual to create a revised version of the audio recording of the message, and then electronically transmit the revised audio recording to an electronic device associated with the target individual.

Abstract: Systems and methods are provided for weakly supervised natural language localization (WSNLL), for example, as implemented in a neural network or model. The WSNLL network is trained with long, untrimmed videos, i.e., videos that have not been temporally segmented or annotated. The WSNLL network or model defines or generates a video-sentence pair, which corresponds to a pairing of an untrimmed video with an input text sentence. According to some embodiments, the WSNLL network or model is implemented with a two-branch architecture, where one branch performs segment sentence alignment and the other one conducts segment selection. These methods and systems are specifically used to predict how a video proposal matches a text query using respective visual and text features.

Abstract: Artificial intelligence systems and methods providing enhanced prediction of information relevant to a conversation are disclosed. The method includes monitoring a conversation between a requestor and a provider. The method also includes determining metadata and text of the conversation. The method further includes determining a regional status of the requestor based on the metadata and text of the conversation, regional information, and regional classification rules. Additionally, the method includes determining a local status of the requestor based on the text of the conversation, the regional status, local information, and local classification rules. Moreover, the method includes determining suggestions based on the regional status, the local status, transactional status information, and transactional classification rules. Further, the method includes providing the suggestions to a user-interface device of the provider.

Abstract: A translation method, implemented by a computer, includes: converting a text written in a first language into a replacement text in which a named entity in the text is replaced with a predetermined character string; translating the replacement text into a second language by using a text translation model which is a neural network; and translating a named entity corresponding to the predetermined character string in the replacement text into the second language by using a named entity translation model which is a neural network.

Abstract: In one embodiment, an electronic device includes an input device configured to provide an input stream, a first processing device, and a second processing device. The first processing device is configured to use a keyword-detection model to determine if the input stream comprises a keyword, wake up the second processing device in response to determining that a segment of the input stream comprises the keyword, and modify the keyword-detection model in response to a training input received from the second processing device. The second processing device is configured to use a first neural network to determine whether the segment of the input stream comprises the keyword and provide the training input to the first processing device in response to determining that the segment of the input stream does not comprise the keyword.

Abstract: Various implementations provide context-based action recommendations based on an incoming communication. To provide the context-based action recommendation, a computing device collects information associated with a user that can be used to generate context information. Upon receiving an incoming communication, the computing device identifies various characteristics associated with the incoming communication. In turn, the computing device analyzes the context information, using the identified characteristics, to identify context information relevant to the incoming communication. Some implementations generate an action recommendation based on the identified context information such as a purchase transaction correlated with a monetary deposit and/or determining a biometric, or vital sign of the user, and notify the user of the action recommendation.

Abstract: An emotion-based voice interaction method, a storage medium and a terminal device, the method comprising: receiving voice information to be processed, and acquiring an intent type of the voice information (S10); when the intent type is an emotion intent, determining an emotion type of the voice information (S20); generating a voice response for the voice interaction according to the emotion type, and playing the voice response (S30). The present method can generate a corresponding voice response according to emotion intent, enabling a voice response to match the emotion intent of the user, both realizing voice interaction and achieving emotional interaction, making use more convenient for a user. The emotion type of the voice information is further determined by comparing pitch, fluctuation and tone with corresponding ranges.

Abstract: A method for localizing a software resource in a second language is disclosed. The method may include receiving a software resource in a first language, receiving data relating to a state of translations performed for the software application by a localization service, determining based on the software resource in the first language and the data whether an up-to-date software resource in a second language exists in a data store where the software resource in the second language corresponds to the software resource in the first language.

Abstract: A transcription of a query for content discovery is generated, and a context of the query is identified, as well as a first plurality of candidate entities to which the query refers. A search is performed based on the context of the query and the first plurality of candidate entities, and results are generated for output. A transcription of a second voice query is then generated, and it is determined whether the second transcription includes a trigger term indicating a corrective query. If so, the context of the first query is retrieved. A second term of the second query similar to a term of the first query is identified, and a second plurality of candidate entities to which the second term refers is determined. A second search is performed based on the second plurality of candidates and the context, and new search results are generated for output.

Abstract: Hardware and/or software systems, devices, networks, and methods of the present invention enable ornamental devices, and interactive electronic devices in general, to generate and react to stimulus from other devices. In various embodiments electronic devices generate one or more pseudo-stimuli and stimuli and/or react to the stimuli generated by other devices mimicking fireflies, other bioluminescent organisms, and other interacting organisms. Pseudo-stimuli generally simulates the physical stimulus of the organism. Whereas the stimulus may include naturally-occurring stimulus, as well as technology generated stimuli to increase system robustness. When a stimulus generated by a first electronic device is detected by one or more second electronic devices, the second devices may react in one or more different methods.

Abstract: A method of generating an editable translated electronic document from an input image of an original document with a first layout includes: segmenting the input image to generate a first region including first untranslated text; extracting, from the first region, the first untranslated text and a first layout information; generating an editable output data including the first untranslated text and the first layout information; translating the first untranslated text into a translated text; editing the output data to include the translated text; and generating, using the first layout information, the translated electronic document including the translated text and a second layout that is identical to the first layout.