Abstract: The present disclosure is generally related to a data processing system to validate vehicular functions in a voice activated computer network environment. The data processing system can improve the efficiency of the network by discarding action data structures and requests that invalid prior to their transmission across the network. The system can invalidate requests by comparing attributes of a vehicular state to attributes of a request state.

Abstract: A greeting card having an audio message recording and playback device permits recording of personalized audio messages to be played upon opening of the greeting card. The recording device is operable in either a trial mode or a use mode. In the trial mode, which would be applicable when the card is displayed in a store, a potential purchaser may experience the functionality of the card by recording their own test message. The test message is played back initially for the potential purchaser but is not subsequently played back to be later heard by other potential purchasers. In the use mode, which the card may be switched to after purchase by the giver of the greeting card, a user recorded message may be played back repeatedly upon subsequent openings of the card. The user recorded message may be followed by a prerecorded recording, such as a song. Additional prerecorded messages, such as voice prompts with instructions for recording a message, may also be included for activation in the trial mode.

Abstract: Devices and techniques are generally described for delayed execution of natural language understanding processes. In various examples, input data is received. In some examples, automatic speech recognition (ASR) data is generated that represents the input data. In some further examples, processing of the ASR data by a first natural language understanding (NLU) process is initiated. In some examples, a first amount of time by which to delay processing of the ASR data by a second NLU process is determined. In at least some examples, processing of the ASR data by the second NLU process is initiated after the first amount of time has elapsed. The first NLU process may be unable to interpret the ASR data. The second NLU process may generate result data that may be stored in memory.

Abstract: A method and apparatus for determining a speech presence probability and an electronic device are provided. According to present disclosure, a metric parameter of a signal to noise ratio of a signal of a first channel and a metric parameter of a signal power level difference between the first channel and the second channel are introduced in determining the speech presence probability, the normalization and non-linear transformation processing is performed on the above-mentioned metric parameters, and the speech presence probability is obtained by fitting the product term and a first power term of a power exponent of the above-mentioned parameters. Therefore, the calculation amount of calculating the speech presence probability is reduced, the calculation result has good robustness to parameter fluctuations, and the disclosure can be widely applied to various application scenarios of dual-microphone speech enhancement systems.

Abstract: A codec allowing for switching between different coding modes is improved by, responsive to a switching instance, performing temporal smoothing and/or blending at a respective transition.

Abstract: A technique for semantic search and retrieval that is event-based, wherein is event is composed of a sequence of observations that are user speech or physical actions. Using a first set of conversations, a machine learning model is trained against groupings of utterances therein to generate a speech act classifier. Observation sequences therein are organized into groupings of events and configured for subsequent event recognition. A set of second (unannotated) conversations are then received. The set of second conversations is evaluated using the speech act classifier and information retrieved from the event recognition to generate event-level metadata that comprises, for each utterance or physical action within an event, one or more associated tags. In response to a query, a search is performed against the metadata. Because the metadata is derived from event recognition, the search is performed against events learned from the set of first conversations.

Abstract: Devices and techniques are generally described for generating and evaluating utterances. In some examples, an utterance generation and evaluation system can receive intent data and target data. The utterance generation and evaluation system can determine related target names and related intent names and, based on the related target names and related intent names, can generate an utterance phrase. The utterance generation and evaluation system can determine a confidence score associated with the utterance phrase and, based on the confidence score, determine the utterance phrase as a recommended utterance phrase.

Abstract: A system includes at least one processor to perform natural language processing on text from at least one document and assign the at least one document to at least one subjective wellbeing dimension by comparing the text from the at least one document with a subjective wellbeing dimension filter for each subjective wellbeing dimension, insert the at least one document into at least one bin, each bin associated with a particular subjective wellbeing dimension, and analyze each document in each bin associated with the particular subjective wellbeing dimension to determine a score for each subjective wellbeing dimension and an overall score that is based on each score for each subjective wellbeing dimension.

Abstract: A system and a method are disclosed for alerting a manager device to an occurrence of an event an agent device during a conversation between the agent device and an external party. N an embodiment, a processor receives transcript data during a conversation between the agent device and the external party. The processor normalizing the transcript data, and inputs the normalized transcript data into a machine learning model, the machine learning model trained to identify an inflection point in the conversation. The processor receives, as output from the machine learning model, a measure of notability of the normalized transcript data. The processor determines whether the measure of notability corresponds to an inflection point, and, responsive to determining that the measure of notability corresponds to an inflection point, alerts the manager device.

Abstract: Disclosed are a method for training speech recognition model, a method and a system for speech recognition. The disclosure relates to field of speech recognition and includes: inputting an audio training sample into the acoustic encoder to represent acoustic features of the audio training sample in an encoded way and determine an acoustic encoded state vector; inputting a preset vocabulary into the language predictor to determine text prediction vector; inputting the text prediction vector into the text mapping layer to obtain a text output probability distribution; calculating a first loss function according to a target text sequence corresponding to the audio training sample and the text output probability distribution; inputting the text prediction vector and the acoustic encoded state vector into the joint network to calculate a second loss function, and performing iterative optimization according to the first loss function and the second loss function.

Abstract: Embodiments are directed to organizing conversation information. A tracker vocabulary may be provided to a universal model to predict a generalized vocabulary associated with the tracker vocabulary. A tracker model may be generated based on the portions of the universal model activated by the tracker vocabulary such that a remainder of the universal model may be excluded from the tracker model. Portions of a conversation stream may be provided to the tracker model. A match score may be generated based on the track model and the portions of the conversation stream such that the match score predicts if the portions of the conversation stream may be in the generalized vocabulary predicted for the tracker vocabulary. Tracker metrics may be collected based on the portions of the conversation and the match scores such that the tracker metrics may be included in reports or notifications.

Abstract: A machine learning method for training a learning model includes: transforming a first audio type of audio data into a first image type of image data, wherein a first audio component and a second audio component are mixed in the first audio type of audio data, and the first image type of image data corresponds to the first audio type of audio data; transforming a second audio type of audio data into a second image type of image data, wherein the second audio type of audio data includes the first audio component without mixture of the second audio component, and the second image type of image data corresponds to the second audio type of audio data; and performing machine learning on the learning model with training data including sets of the first image type of image data and the second image type of image data.

Abstract: A method for detecting a hotword includes receiving a sequence of input frames that characterize streaming audio captured by a user device and generating a probability score indicating a presence of a hotword in the streaming audio using a memorized neural network. The network includes sequentially-stacked single value decomposition filter (SVDF) layers and each SVDF layer includes at least one neuron. Each neuron includes a respective memory component, a first stage configured to perform filtering on audio features of each input frame individually and output to the memory component, and a second stage configured to perform filtering on all the filtered audio features residing in the respective memory component. The method also includes determining whether the probability score satisfies a hotword detection threshold and initiating a wake-up process on the user device for processing additional terms.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for hotword detection on multiple devices are disclosed. In one aspect, a method includes the actions of receiving, by a first computing device, audio data that corresponds to an utterance. The actions further include determining a first value corresponding to a likelihood that the utterance includes a hotword. The actions further include receiving a second value corresponding to a likelihood that the utterance includes the hotword, the second value being determined by a second computing device. The actions further include comparing the first value and the second value. The actions further include based on comparing the first value to the second value, initiating speech recognition processing on the audio data.

Abstract: An entity grammar that specifies a computer conversational agent may be received. User utterances are interpreted based on the entity grammar and prompts for the conversational agent to pose are determined based on the entity grammar. An outcome of the dialog is built by storing words in the user utterances and the prompts that match tokens in the entity grammar. The entity grammar specifies both a dialog flow and data structure of the outcome.

Abstract: In one embodiment, a method includes generating audio segments from a speech signal, generating latent representations that respectively correspond to the audio segments, the latent representations comprising a first subset and a second subset, generating quantized representations that respectively correspond to the latent representations, masking the second subset of the latent representations, using a machine-learning model to process the first subset of the latent representations and the masked second subset of the latent representations to generate contextualized representations that respectively correspond to the latent representations, pre-training the machine-learning model based on comparisons between (1) a subset of the contextualized representations that respectively correspond to the masked second subset of the latent representations and (2) a subset of the quantized representations that respectively correspond to the masked second subset of the latent representations, and training the pre-trained

Abstract: Devices and techniques are generally described for a speech processing routing architecture. In various examples, first data comprising a first feature definition is received. The first feature definition may include a first indication of first source data and first instructions for generating feature data using the first source data. In various examples, the feature data may be generated according to the first feature definition. In some examples, a speech processing system may receive a first request to process a first utterance. The feature data may be retrieved from a non-transitory computer-readable memory. The speech processing system may determine a first skill for processing the first utterance based at least in part on the feature data.

Abstract: Aspects relate to apparatuses and methods for linking posting data to a plurality of user identifiers. An exemplary apparatus includes a processor and a memory communicatively connected to the processor, the memory containing instructions configuring the processor to receive a plurality of user identifiers relating to a plurality of users, receive posting data from a posting generator of a plurality of posting generators, identify a plurality of keywords within the posting data, generate a keyword ranking, match a plurality of keywords of the keyword ranking to the plurality of user identifiers, and generate, as a function of the matching, a ranking of the plurality of user identifiers based on a superiority criterion of each user identifier using a fuzzy set inference system.

Abstract: Provided are a dialogue device, a dialogue method, a data structure, and a program capable of realizing various dialogues while reducing the amount of description of a dialogue scenario. A knowledge transition unit 120 determines a next type of knowledge based on: a knowledge base 130 in which a relation label indicating each of relations between a plurality of types of knowledge is attached to knowledge about each of utterances to express the knowledge about the utterance; a user utterance; current knowledge; and a dialogue scenario including a basic scenario in which a transition method between the plurality of types of knowledge in the knowledge base is determined using the relation label, and an utterance generation unit 150 generates a system utterance based on the next type of knowledge.

Abstract: The present disclosure discloses an image processing device including: a receiving module configured to receive a voice signal and an image to be processed; a conversion module configured to convert the voice signal into an image processing instruction and determine a target area according to a target voice instruction conversion model, in which the target area is a processing area of the image to be processed; and a processing module configured to process the target area according to the image processing instruction and a target image processing model. The examples may realize the functionality of using voice commands to control image processing, which may save users' time spent in learning image processing software prior to image processing, and improve user experience.