Abstract: Modulating packetized audio signals in a voice activated data packet based computer network environment is provided. A system can receive audio signals detected by a microphone of a device. The system can parse the audio signal to identify trigger keyword and request, and generate a first action data structure. The system can identify a content item object based on the trigger keyword, and generate an output signal comprising a first portion corresponding to the first action data structure and a second portion corresponding to the content item object. The system can apply a modulation to the first or second portion of the output signal, and transmit the modulated output signal to the device.

Abstract: Remote automated assistant component(s) generate client device notification(s) based on a received IoT state change notification that indicates a change in at least one state associated with at least one IoT device. The generated client device notification(s) can each indicate the change in state associated with the at least one IoT device, and can optionally indicate the at least one IoT device. Further, the remote automated assistant component(s) can identify candidate assistant client devices that are associated with the at least one IoT device, and determine whether each of the one or more of the candidate assistant client device(s) should render a corresponding client device notification.

Abstract: A learning data acquisition device or the like, capable of acquiring learning data by superimposing noise data on clean voice data at an appropriate SN ratio, is provided. The learning data acquisition device includes a voice recognition influence degree calculation unit and a learning data acquisition unit. The voice recognition influence degree calculation unit calculates an influence degree on voice recognition accuracy caused by a change of a signal-to-noise ratio, based on a result of voice recognition on the kth noise superimposed voice data and a result of voice recognition on the k?1th noise superimposed voice data, where K is an integer of 2 or larger, k=2, 3, . . .

Abstract: Certain aspects of the present disclosure provide techniques for providing sentiment analysis of content. In order to determine the overall sentiment of content, a request is received by a sentiment analyzer, which then identifies a content identification number and retrieves comments associated with the content identification number. The sentiment analyzer pre-processes the comments, which includes removing all personal identifying information from the comments. The sentiment analyzer sends the pre-processed comments to a natural language processing service, and in turn, receives sentiment indications corresponding to the comments provided. Based on the sentiment scores, the sentiment analyzer generates a sentiment analysis and displays the sentiment analysis in the graphical user interface generated by the sentiment analyzer.

Abstract: Techniques for identifying one or more missing fragments within input text are disclosed. A discourse tree (DT) is generated for the input text (IT) received, the IT having any suitable number of sentence fragments. An indication that the IT is likely missing one or more sentence fragments may be identified based on determining that one or more rhetorical relationships of the DT matches one of a set of predefined rhetorical relationships. A query is generated one or more sentence fragments of the IT and executed against a knowledge base to obtain a set of search results. A most-relevance search result can be utilized to identify a set of candidate sentence fragments. A subset of those candidate sentence fragments can be identified based on comparing them to the sentence fragments provided in the IT, each candidate sentence fragment of the subset being implied but excluded from the IT.

Abstract: A digital assistant supported on devices such as smartphones, tablets, personal computers, game consoles, etc. includes an extensibility client that exposes an interface and service that enables third party applications to be integrated with the digital assistant so the application user experiences are rendered using the native voice of the digital assistant. Specific voice inputs associated with a given application may be registered by developers using a manifest that is loaded when the application is launched on the device so that voice inputs from the device user can be mapped by the digital assistant extensibility client to the appropriate application as input events for consumption. In typical implementations, the manifest is arranged as a declarative document that streamlines application development and provides a seamless user experience by enabling customization of third party applications to integrate the digital assistant's voice and behaviors within the user experience of the application's domain.

Abstract: Examples of the present disclosure describe systems and methods for multichannel audio speech classification. In examples, an audio signal comprising multiple audio channels is received at a processing device. Each of the audio channels in the audio signal is transcoded to a predefined audio format. For each of the transcoded audio channels, an average power value is calculated for one or more data windows in the audio signal. A correlation value is calculated between the average power value for each audio channel and the combined average power value of the other audio channels in the audio signal. Each of the correlation values (or an aggregated correlation value for the audio channels) is then compared against a threshold value to determine whether the audio signal is to be classified as a speech-based communication. Based on the classification, an action associated with the audio signal may be performed.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for detecting a continued conversation are disclosed. In one aspect, a method includes the actions of receiving first audio data of a first utterance. The actions further include obtaining a first transcription of the first utterance. The actions further include receiving second audio data of a second utterance. The actions further include obtaining a second transcription of the second utterance. The actions further include determining whether the second utterance includes a query directed to a query processing system based on analysis of the second transcription and the first transcription or a response to the first query. The actions further include configuring the data routing component to provide the second transcription of the second utterance to the query processing system as a second query or bypass routing the second transcription.

Abstract: According to an aspect of the present invention an encoder for encoding an audio signal has an analyzer configured for deriving prediction coefficients and a residual signal from a frame of the audio signal. The encoder has a formant information calculator configured for calculating a speech related spectral shaping information from the prediction coefficients, a gain parameter calculator configured for calculating a gain parameter from an unvoiced residual signal and the spectral shaping information and a bitstream former configured for forming an output signal based on an information related to a voiced signal frame, the gain parameter or a quantized gain parameter and the prediction coefficients.

Abstract: Techniques for processing voice commands from a locked device are described. A voice command received by a locked device is stored, a prompt requesting that the device be unlocked is generated, and the voice command is processed automatically after the device is unlocked. Thus, the system processes the voice command without the user repeating the voice command. In addition, the system may process certain voice commands even when the device is locked. For example, a whitelist filter compares an intent associated with the voice command to whitelisted intents from a whitelist database before the intent is dispatched to a speechlet, and intents included in the whitelist database are processed normally. Thus, the system performs certain voice commands while the device is locked, while other voice commands may be automatically processed after the device is unlocked without the user repeating the voice command.

Abstract: A regular expression prompt may be determined by combining a regular expression prompt template with input text from an input document. The regular expression prompt template may include a natural language instruction to identify one or more regular expressions from the input text and one or more fillable portions designated for filling with the input text. The regular expression prompt may be sent to a large language model for evaluation, and one or more regular expressions may be identified based on a response received from the large language model. The regular expressions may be used to disaggregate the input text, and the disaggregated text portions may be used to determine a structured document based on the input document. The structured document may be used to determine a response to a query of the input document.

Abstract: A method of detecting a cough in an audio stream includes a step of performing one or more pre-processing steps on the audio stream to generate an input audio sequence comprising a plurality of time-separated audio segments. An embedding is generated by a self-supervised triplet loss embedding model for each of the segments of the input audio sequence using an audio feature set, the embedding model having been trained to learn the audio feature set in a self-supervised triplet loss manner from a plurality of speech audio clips from a speech dataset. The embedding for each of the segments is provided to a model performing cough detection inference. This model generates a probability that each of the segments of the input audio sequence includes a cough episode. The method includes generating cough metrics for each of the cough episodes detected in the input audio sequence.

Abstract: Techniques for configuring a speech processing system with a privacy mode that is associated with the identity of a user that activated the privacy mode are described. A user may speak an indication to have the speech processing system activate a privacy mode. When such an indication is detected by the speech processing system, the speech processing system determines an identity of the user, determines a unique system identifier associated with the user, and generates a privacy mode flag. The speech processing system then associates the privacy mode flag with the user's unique system identifier. The privacy mode flag indicates to components of the speech processing system that any data related to processing of the user's utterances should not be sent to long term storage, thus causing various components of the system to delete data once the respective component is finished processing with respect to an utterance of the user.

Abstract: This application discloses an artificial intelligence-based (AI-based) wakeup word detection method performed by a computing device. The method includes: constructing, by using a preset pronunciation dictionary, at least one syllable combination sequence for self-defined wakeup word text inputted by a user; obtaining to-be-recognized speech data, and extracting speech features of speech frames in the speech data; inputting the speech features into a pre-constructed deep neural network (DNN) model, to output posterior probability vectors of the speech features corresponding to syllable identifiers; determine a target probability vector from the posterior probability vectors according to the syllable combination sequence; and calculate a confidence according to the target probability vector, and determine that the speech frames include the wakeup word text when the confidence is greater than or equal to a threshold.

Abstract: A process receives, with a processor, audio corresponding to media content. Further, the process converts, with the processor, the audio to text. In addition, the process concatenates, with the processor, the text with one or more time codes. The process also parses, with the processor, the concatenated text into one or more text chunks according to one or more subtitle parameters. Further, the process automatically translates, with the processor, the parsed text from a first spoken language to a second spoken language. Moreover, the process determines, with the processor, if the language translation complies with the one or more subtitle parameters. Additionally, the process outputs, with the processor, the language translation to a display device for display of the one or more text chunks as one or more subtitles at one or more times corresponding to the one or more time codes.

Abstract: Audio decoder device for decoding a bitstream, the audio decoder device including: a predictive decoder for producing a decoded audio frame from the bitstream, wherein the predictive decoder includes a parameter decoder for producing one or more audio parameters for the decoded audio frame from the bitstream and wherein the predictive decoder includes a synthesis filter device for producing the decoded audio frame by synthesizing the one or more audio parameters for the decoded audio frame; a memory device including one or more memories, wherein each of the memories is configured to store a memory state for the decoded audio frame, wherein the memory state for the decoded audio frame of the one or more memories is used by the synthesis filter device for synthesizing the one or more audio parameters for the decoded audio frame; and a memory state resampling device configured to determine the memory state for synthesizing the one or more audio parameters for the decoded audio frame, which has a sampling rate, f

Abstract: A method executed by a computing device includes determining a set of identigens for each phrase word of a phrase to produce sets of identigens. A set of identigens of the sets of identigens represents one or more different meanings of a phrase word of the phrase. The method further includes obtaining inflection information for one or more phrase words of the phrase. The method further includes selecting an identigen of a first set of identigens based on the inflection information to produce a first identigen selection for the first set of identigens having a selected meaning of one or more different meanings of the first phrase word. The method further includes interpreting remaining sets of identigens of the sets of identigens to produce an entigen group so that the entigen group represents a most likely meaning interpretation of the phrase.

Abstract: A method and system for detecting and localizing a target audio event in an audio clip is disclosed. The method and system use utilizes a hierarchical approach in which a dilated convolutional neural network to detect the presence of the target audio event anywhere in an audio clip based on high level audio features. If the target audio event is detected somewhere in the audio clip, the method and system further utilizes a robust audio vector representation that encodes the inherent state of the audio as well as a learned relationship between state of the audio and the particular target audio event that was detected in the audio clip. A bi-directional long short term memory classifier is used to model long term dependencies and determine the boundaries in time of the target audio event within the audio clip based on the audio vector representations.

Abstract: An encoder for encoding an audio signal has: an analyzer configured for deriving prediction coefficients and a residual signal from an unvoiced frame of the audio signal; a gain parameter calculator configured for calculating a first gain parameter information for defining a first excitation signal related to a deterministic codebook and for calculating a second gain parameter information for defining a second excitation signal related to a noise-like signal for the unvoiced frame; and a bitstream former configured for forming an output signal based on an information related to a voiced signal frame, the first gain parameter information and the second gain parameter information.

Abstract: The present disclosure provides a method for denoising voice data, an electronic device, and a computer readable storage medium. The present disclosure relates to the technical field of artificial intelligence, such as Internet of Vehicles, smart cockpit, smart voice, and voice recognition. A specific embodiment of the method includes: receiving an input to-be-played first piece of voice data; and invoking, in response to not detecting a synthetic voice interruption signal in a process of playing the first piece of voice data, a preset first denoising algorithm to filter out noise data except for the first piece of voice data.