Abstract: Video processing with a multi-quality loop filter using a multi-task neural network is performed by at least one processor and includes generating a first set of masked weight parameters, based on an input and a plurality of quantization parameter values with a corresponding first set of masks and first plurality of weight parameters, for a first set of shared neural network layers, selecting a second set of task specific neural network layers for the plurality of quantization parameter values with a second plurality of weight parameters, based on the plurality of quantization parameter values, computing an inference output, based on the first set of masked weight parameters and the second plurality of weight parameters, and outputting the computed inference output as an enhanced result.

Abstract: Disclosed is a hyperspectral data analysis method based on a semi-supervised learning strategy, which includes: hyperspectral sample data is acquired; a sample training set and a prediction set are constructed, herein an unlabeled prediction set sample is used; a regression network based on a generative adversarial network is constructed, including a generator network that generates a sample, and a discriminator/regressor network that has functions of judging the authenticity of the sample and outputting a quantitative analysis value at the same time; a loss function of the generative adversarial network is constructed, including a loss function of the discriminator, a loss function of the regressor, and a loss function of the generator with a sample distribution matching function. The generative adversarial network is used to generate a sample. A sample distribution matching strategy is used to supplement an existing unlabeled sample set. So, the accuracy of hyperspectral quantitative analysis is improved.

Abstract: The present invention discloses a spiking neural network for classifying input signals. The spiking neural network comprises a plurality of spiking neurons, and a plurality of synaptic elements interconnecting the spiking neurons to form the network. Each synaptic element is adapted to receive a synaptic input signal and apply a weight to the synaptic input signal to generate a synaptic output signal, the synaptic elements being configurable to adjust the weight applied by each synaptic element. Furthermore, each of the spiking neurons is adapted to receive one or more of the synaptic output signals from one or more of the synaptic elements, and generate a spatio-temporal spike train output signal in response to the received one or more synaptic output signals. The spiking neural network is partitioned into multiple sub-networks, wherein each sub-network comprises a sub-set of the spiking neurons connected to receive synaptic output signals from a sub-set of the synaptic elements.

Abstract: Systems and methods are described for training a model for detecting manufacturing anomalies. A test response parameter is identified at a computing device, and a first plurality of component waveforms associated with the test response parameter are received at the computing device. Each waveform of the plurality of waveforms comprises a plurality of datapoints. A model is generated at the computing device, and the model is trained at the computing device and on the first plurality of component waveforms, thereby generating one or more parameters associated with the model. A second plurality of component waveforms associated with the test response parameter is received, and the trained model is accessed. It is indicated using the trained model, whether any of the second plurality of component waveforms comprises an anomaly. For each indicated waveform, the indicated waveform is reviewed and, for each reviewed waveform not comprising an anomaly, the waveform is labelled.

Abstract: A social agent system includes a computing platform having processing hardware and a system memory storing a social agent software code. The processing hardware is configured to execute the social agent software code to receive, from a client system, input data provided by a user of the client system when the user is interacting with the social agent system using the client system, and to select, using the input data, a dialogue template for responding to the user. The dialogue template includes one or more placeholder fields to be filled by the client system to create a personalized dialogue for responding to the user. The processing hardware is further configured to execute the social agent software code to deliver, to the client system, the dialogue template including the one or more placeholder fields to be filled by the client system to create the personalized dialogue for responding to the user.

Abstract: A method for driving path prediction is provided. The method concatenates past trajectory features and lane centerline features in a channel dimension at an agent's respective location in a top view map to obtain concatenated features thereat. The method obtains convolutional features derived from the top view map, the concatenated features, and a single representation of the training scene the vehicle and agent interactions. The method extracts hypercolumn descriptor vectors which include the convolutional features from the agent's respective location in the top view map. The method obtains primary and auxiliary trajectory predictions from the hypercolumn descriptor vectors. The method generates a respective score for each of the primary and auxiliary trajectory predictions.

Abstract: A computing system obtains text that includes words and provides the text as input to an emotional classifier model that has been trained based upon emotional classification. The computing system obtains a textual embedding of the computer-readable text as output of the emotional classifier model. The computing system generates a phoneme sequence based upon the words of the text. The computing system, generates, by way of an encoder of a text to speech (TTS) model, a phoneme encoding based upon the phoneme sequence. The computing system provides the textual embedding and the phoneme encoding as input to a decoder of the TTS model. The computing system causes speech that includes the words to be played over a speaker based upon output of the decoder of the TTS model, where the speech reflects an emotion underlying the text due to the textual embedding provided to the encoder.

Abstract: Frequent sequences extracted from a set of documents according to a common rule are obtained. Based on comparing occurrence frequencies of various sequences, confidence of the first frequent sequence being a label expression representing a document part in a target document is evaluated. Keywords are extracted from the target document based on evaluation of the confidence.

Abstract: Provided is a process including: receiving a data token to be passed from a first node to a second node; retrieving machine learning model attributes from a collection of one or more of the sub-models of a federated machine-learning model; determining based on the machine learning model attributes, that the data token is learning relevant to members of the collection of one or more of the sub-models and, in response, adding the data toke to a training set to be used by at least some members of the collection of one or more of the sub-models; determining a collection of data tokens to transmit from the second node to a third node of the set of nodes participating in a federated machine-learning model; and transmitting the collection of data tokens.

Abstract: A speech module is joint trained with a knowledge module by transforming a first knowledge graph into an acoustic knowledge graph. The knowledge module is trained on the acoustic knowledge graph. Then, the knowledge module is integrated with the speech module to generate an integrated knowledge-speech module. In some instances, the speech module included in the integrated knowledge-speech module is aligned with a language module to generate an optimized speech model configured to leverage acoustic information and acoustic-based knowledge information, along with language information.

Abstract: A computer-implemented method for counterfactual conversation simulation is disclosed. The computer-implemented method includes generating a system output based, at least in part, on a user input. The computer-implemented method further includes determining that a system output/user input pair is not satisfactory based, at least in part, on a system output/user input score being below a predetermined threshold. The computer-implemented method further includes generating, in response to determining the system output/user input pair is not satisfactory, a counterfactual simulation of the user input based, at least in part, on a target intent of the user input.

Abstract: A method for determining a category responsive to a user query is disclosed. The method includes receiving a training data set comprising a plurality of data pairs, each data pair including: (i) a query; and (ii) an associated one or more categories that are responsive to the query, wherein the one or more categories in the training data set defines a plurality of categories. The method includes training a machine learning algorithm, according to the training data set, to create a trained model, wherein training the machine learning algorithm includes: creating a first co-occurrence data structure defining co-occurrence of respective word representations of the queries with the plurality of categories, and creating a second co-occurrence data structure defining co-occurrence of respective categories in respective data pairs. The method also includes deploying the trained model to return one or more categories in response to a new query input.

Abstract: Systems and methods are described for providing subtitles for a media content item. Subtitles are obtained, using control circuitry, for the media content item. Control circuitry determines whether a character component of the subtitles should be replaced by an image component. In response to determining that the character component of the subtitles should be replaced by an image component, control circuitry selects, from memory, an image component corresponding to the character component. Control circuitry replaces the character component of the subtitles by the image component to generate modified subtitles.

Abstract: Disclosed is an electronic device including a communication interface, a memory, a microphone, a speaker, a display, a main processor, and a sub-processor activating the main processor by recognizing a wake-up word included in a voice input. The at least one memory stores instructions that, when executed, cause the main processor to receive a first voice input to register the wake-up word, when the first voice input does not include a specified word, to receive a second voice input including a word identical to the first voice input, through the microphone, to generate a wake-up word recognition model for recognizing the wake-up word, and to store the generated wake-up word recognition model in the at least one memory, and when the first voice input includes the specified word, to output information for requesting a third voice input, through the speaker or the display.

Abstract: A computer-implemented method is provided for estimating output confidence of a black box Application Programming Interface (API). The method includes generating paraphrases for an input text. The method further includes calculating a distance between the input text and each respective one of the paraphrases. The method also includes sorting the paraphrases in ascending order of the distance. The method additionally includes selecting a top predetermined number of the paraphrases. The method further includes inputting the input text and the selected paraphrases into the API to obtain an output confidence score for each of the input text and the selected paraphrases. The method also includes estimating, by a hardware processor, the output confidence of the input text from a robustness of output scores of the input text and the selected paraphrases.

Abstract: Techniques for conversational-based searching are described. A system may receive a first spoken user input, and may determine that the first spoken user input corresponds to a request for information associated with an entity. The system may retrieve item results corresponding to the entity. The system may determine a suggested user input based on the retrieved item results, and may determine output data corresponding to the suggested user input. The system may send output data to a user device, where the output data includes the item results and the suggested user input. The system may receive a second spoken user input, and may determine that the second spoken user input corresponds to the suggested user input. In response, the system may send the previously determined output data to the device.

Abstract: Implementations relate to effectively localizing system responses, that include dynamic information, to target language(s), such that the system responses are grammatical and/or natural in the target language(s). Some of those implementations relate to various techniques for resource efficient generation of templates for a target language. Some versions of those implementations relate to resource efficient generation of target language natural language generation (NLG) templates and, more particularly, to techniques that enable a human user to generate a target language NLG template more efficiently and/or with greater accuracy. The more efficient target language NLG template generation enables less utilization of various client device resources and/or can mitigate the risk of flawed NLG templates being provided for live use in one or more systems.

Abstract: There is inter alia disclosed an apparatus for spatial audio encoding which can receive or determine for one or more audio signals (102), spatial audio parameters (106) on a sub band basis for providing spatial audio reproduction, the spatial audio parameters can comprise a coherence value (112) for each sub band of a plurality of subbands (202) of a frame. The apparatus then determines a significance measure for the coherence values (401) of the plurality of sub bands of the frame and uses the significance measure to determine whether to encode (403) the coherence values of the plurality of sub bands of the frame.

Abstract: A method in an interactive computing-system includes pre-processing an input natural-language (NL) from a user command based on natural language processing (NLP) for classifying speech information and non-speech information, obtaining an NLP result from the user command, fetching a device specific information from one or more IoT devices operating in an environment based on the NLP result, generating one or more contextual parameters based on the NLP result and the device specific information, selecting at least one speaker embedding stored in a database for the one or more IoT devices based on the one or more contextual parameters, and outputting the selected at least one speaker embedding for playback to the user.

Abstract: A system and method code an object-based audio signal comprising audio objects in response to audio streams with associated metadata. In the system and method, a metadata processor codes the metadata and generates information about bit-budgets for the coding of the metadata of the audio objects. An encoder codes the audio streams while a bit-budget allocator is responsive to the information about the bit-budgets for the coding of the metadata of the audio objects from the metadata processor to allocate bitrates for the coding of the audio streams by the encoder.