Abstract: A system and method for voice control of a media playback device is disclosed. The method includes receiving an instruction of a voice command, converting the voice command to text, transmitting the text command to the playback device, and having the playback device execute the command. An instruction may include a command to play a set of audio tracks, and the media playback device plays the set of audio tracks upon receiving the instruction.

Abstract: Implementations relate to generating multi-modal response(s) through utilization of large language model(s) (LLM(s)). Processor(s) of a system can: receive natural language (NL) based input, generate a multi-modal response that is responsive to the NL based output, and cause the multi-modal response to be rendered. In some implementations, and in generating the multi-modal response, the processor(s) can process, using a LLM, LLM input (e.g., that includes at least the NL based input) to generate LLM output, and determine, based on the LLM output, textual content for inclusion in the multi-modal response and multimedia content for inclusion in the multi-modal response. In some implementations, the multimedia content can be obtained based on a multimedia content tag that is included in the LLM output and that is indicative of the multimedia content. In various implementations, the multimedia content can be interleaved between segments of the textual content.

Abstract: An information processing method, a system, an apparatus, an electronic device and a storage medium, where the method is applied to a client, and includes: receiving a transcript and a sentence identifier of the transcript sent by a service server; reading a local sentence identifier, and when the received sentence identifier is the same as the local sentence identifier, updating a displayed caption content corresponding to the local sentence identifier with the transcript. When the received sentence identifier of the client is the same as the local sentence identifier, the displayed caption content is replaced with the received transcript.

Abstract: Systems and methods for natural language processing are described. One or more embodiments of the present disclosure generate a word embedding for each word of an input phrase, wherein the input phrase indicates a sentiment toward an aspect term, compute a gate vector based on the aspect term, identify a dependency tree representing relations between words of the input phrase, generate a representation vector based on the dependency tree and the word embedding using a graph convolution network, wherein the gate vector is applied to a layer of the graph convolution network, and generate a probability distribution over a plurality of sentiments based on the representation vector.

Abstract: A method for extracting a kansei adjective of a product based on principal component analysis and explanation (PCA-E) includes constructing a product kansei evaluation vector matrix through original kansei adjectives; performing dimensionality reduction through PCA; and determining, based on principal component load factors, kansei adjectives representing principal components. In this way, the kansei adjectives extracted are explanatory to help users understand the selected kansei adjectives and make accurate evaluation.

Abstract: A system for activating a cued health assessment, which includes an audio receiver for receiving voice samples to measure one of a plurality of voice biomarkers, an audio processing module for extracting one of a plurality of biomarkers from the received voice samples, the audio processing module further classifies the received voice samples to one of plurality of predetermined health states according to the extracted biomarkers, and a voice sample scheduler for activating a cued health assessment module when the classified health state is a clinically actionable health state.

Abstract: Generate, for each of the words of a common vocabulary of first and second text corpora, a first word embedding vector in the first text corpus and a second word embedding vector in the second text corpus. Generate, for each word in a random sample of non-landmark words, an artificially shifted word embedding vector by modifying the first word embedding vector for that word. Train a machine learning classifier to predict whether an artificial shift has been injected for a given word, based on the artificially shifted word embedding vector and the second word embedding vector for the given word. Predict semantic shifts for at least a plurality of the words of the common vocabulary by providing the first word embedding vectors and the second word embedding vectors for at least the plurality of the words of the common vocabulary as input to the trained machine learning classifier.

Abstract: A method for receiving processed information at a remote device is described. The method includes transmitting from the remote device a verbal request to a first information provider and receiving a digital message from the first information provider in response to the transmitted verbal request. The digital message includes a symbolic representation indicator associated with a symbolic representation of the verbal request and data used to control an application. The method also includes transmitting, using the application, the symbolic representation indicator to a second information provider for generating results to be displayed on the remote device.

Abstract: A device may receive audio data based on a capturing of sounds associated with a structure. The device may obtain a model associated with the structure. The model may have been trained to receive the audio data as input, determine a score that identifies a likelihood that a sound is present in the audio data, and identify the sound based on the score. The device may determine at least one parameter associated with the sound. The device may generate a metric based on the at least one parameter associated with the sound, and perform an action based on the metric.

Abstract: A system is provided for streaming media content in a vehicle. The system includes a personal media streaming appliance system configured to connect to a media delivery system and receive media content from the media delivery system at least via a cellular network. The personal media streaming appliance system operates to transmit a media signal representative to the received media content to a vehicle media playback system so that the vehicle media playback system operates to play the media content in the vehicle. Customized voice communications are generated based on receiving input, such as a user query and/or a media track change indication.

Abstract: Approaches for cross-lingual regularization for multilingual generalization include a method for training a natural language processing (NLP) deep learning module. The method includes accessing a first dataset having a first training data entry, the first training data entry including one or more natural language input text strings in a first language; translating at least one of the one or more natural language input text strings of the first training data entry from the first language to a second language; creating a second training data entry by starting with the first training data entry and substituting the at least one of the natural language input text strings in the first language with the translation of the at least one of the natural language input text strings in the second language; adding the second training data entry to a second dataset; and training the deep learning module using the second dataset.

Abstract: A user device (e.g., voice assistant device, voice enabled device, smart device, computing device, etc.) may receive/detect audio content (e.g., speech, etc.) that includes a wake word and/or words similar to a wake word. The user device may require a wake word, a portion of the wake word, or words similar to the wake word to be detected prior to interacting with a user. The user device may, based on characteristics of the audio content, determine if the audio content originates from an authorized user. The user device may decrease and/or increase scrutiny applied to wake word detection based on whether audio content originates from an authorized user.

Abstract: In one example, a method includes receiving audio data generated by one or more microphones of a computing device, the audio data representing a spoken utterance; identifying, based on the audio data, a user that provided the spoken utterance; identifying, based on the audio data, an automation action associated with one or more automation devices, the automation action corresponding to the spoken utterance; determining whether the identified user is authorized to cause performance of the identified automation action; and responsive to determining that the identified user is authorized to cause performance of the identified automation action, causing the one or more automation devices to perform the identified automation action.

Abstract: A display apparatus and a method for questions and answers includes a display unit includes an input unit configured to receive user's speech voice; a communication unit configured to perform data communication with an answer server; and a processor configured to create and display one or more question sentences using the speech voice in response to the speech voice being a word speech, create a question language corresponding to the question sentence selected from among the displayed one or more question sentences, transmit the created question language to the answer server via the communication unit, and, in response to one or more answer results related to the question language being received from the answer server, display the received one or more answer results. Accordingly, the display apparatus may provide an answer result appropriate to a user's question intention although a non-sentence speech is input.

Abstract: A method and apparatus that dynamically adjust operational parameters of a text-to-speech engine in a speech-based system are disclosed. A voice engine or other application of a device provides a mechanism to alter the adjustable operational parameters of the text-to-speech engine. In response to one or more environmental conditions, the adjustable operational parameters of the text-to-speech engine are modified to increase the intelligibility of synthesized speech.

Abstract: For assertion detection from clinical text in a medical system, a model, such as a neural network, is trained to operate on multi-labeled clinical text. Using multi-task learning, both the scope and the class losses are minimized. As a result, a machine learning model can predict both the scope and class of clinical text for a patient where the clinical text is not limited to one class or a particular length.

Abstract: A method and apparatus that dynamically adjust operational parameters of a text-to-speech engine in a speech-based system are disclosed. A voice engine or other application of a device provides a mechanism to alter the adjustable operational parameters of the text-to-speech engine. In response to one or more environmental conditions, the adjustable operational parameters of the text-to-speech engine are modified to increase the intelligibility of synthesized speech.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for distributing the performance of speech recognition among a remote control device and a voice platform in the cloud. In some embodiments, the remote control device operates to receive a voice input from a user. The remote control device detects a trigger word in the voice input. The remote control device then processes the voice input. The remote control device then transmits the voice input to a voice platform based on the detecting in order to determine an intent associated with the voice input.

Abstract: An optimization method for an implementation of mel-frequency cepstral coefficients is provided. The optimization method includes the following steps: performing a framing step, including using a 400×16 static random access memory to temporarily store a plurality of sampling points of a sound signal with overlap, and decomposing the sound signal into a plurality of frames. Each of the plurality of frames is 400 of the sampling points, there is an overlapping region between adjacent two of the plurality of frames, and the overlapping region includes 240 of the sampling points. The optimization method further includes performing a windowing step, which includes multiplying each of the plurality of frames by a window function in a bit-level design, and the optimization method includes performing a fast Fourier transform (FFT) step, which includes applying a 512 point FFT on a frame signal to obtain a corresponding frequency spectrum.

Abstract: This document generally describes systems and methods for dynamically adapting speech recognition for individual voice queries of a user using class-based language models. The method may include receiving a voice query from a user that includes audio data corresponding to an utterance of the user, and context data associated with the user. One or more class models are then generated that collectively identify a first set of terms determined based on the context data, and a respective class to which the respective term is assigned for each respective term in the first set of terms. A language model that includes a residual unigram may then be accessed and processed for each respective class to insert a respective class symbol at each instance of the residual unigram that occurs within the language model. A transcription of the utterance of the user is then generated using the modified language model.