Abstract: Techniques are described for selectively adapting and/or selectively utilizing a noise reduction technique in detection of one or more features of a stream of audio data frames. For example, various techniques are directed to selectively adapting and/or utilizing a noise reduction technique in detection of an invocation phrase in a stream of audio data frames, detection of voice characteristics in a stream of audio data frames (e.g., for speaker identification), etc. Utilization of described techniques can result in more robust and/or more accurate detections of features of a stream of audio data frames in various situations, such as in environments with strong background noise. In various implementations, described techniques are implemented in combination with an automated assistant, and feature(s) detected utilizing techniques described herein are utilized to adapt the functionality of the automated assistant.

Abstract: The invention provides a content playback system comprising a plurality of playback devices, each of which is configured to detect a voice command from a user and to play content. The system is configured to store an account conversation state associated with an account shared by the plurality of playback devices, and a device conversation state that is associated with a first playback device of the plurality of playback devices. When a voice command is detected by the first playback device, the system is configured to control the first playback device using information in the account conversation state and the device conversation state associated with the first playback device as an input. This may improve continuity of experience for a user across the plurality of playback devices.

Abstract: According to one embodiment, an electronic device determines whether one or more devices should be controlled based on a second utterance input subsequent to a first utterance input from outside in accordance with the first utterance. The electronic device includes a management unit and a controller. The management unit prepares and manages a determination audio data item for determining whether the first utterance is a desired utterance by utterances input from outside at a plurality of times, and determines whether the first utterance is the desired utterance using the prepared and managed determination audio data item. The controller controls the one or more devices based on the second utterance.

Abstract: Embodiments of the specification provide a human-computer interaction processing system, method, storage medium, and electronic device thereof. The method comprises: describing an interaction task in an interaction scenario; performing interaction process control for a current interaction input in the interaction scenario based on the interaction task; and determining an expected next interaction input in the interaction scenario corresponding to the current interaction input based on the interaction process control.

Abstract: A system for enhanced processing of voice-based signals in a voice-controllable sound-generating system (SGS) is provided. An SGS audio source may communicate electronic SGS audio signals to both (a) one or more speakers, which output corresponding SGS sound waves and (b) an audio countering system. A microphone may detect sound waves and output corresponding audio signals including: (a) distorted SGS audio signals corresponding with SGS sound waves and (b) additional audio signals originated from other sources, e.g., including voice-based commands. The audio countering system may (a) receive the electronic SGS audio signals from the SGS audio source; receive signals from the microphone representing the microphone-detected sound waves, and (c) use the electronic SGS audio signals received to cancel or counter the distorted SGS audio signals included in the microphone-received audio signals, to thereby enhance any voice-based commands included in the received audio signals.

Abstract: Embodiments relate to an audio processing unit that includes a buffer, bitstream payload deformatter, and a decoding subsystem. The buffer stores at least one block of an encoded audio bitstream. The block includes a fill element that begins with an identifier followed by fill data. The fill data includes at least one flag identifying whether enhanced spectral band replication (eSBR) processing is to be performed on audio content of the block. A corresponding method for decoding an encoded audio bitstream is also provided.

Abstract: Systems and methods for device naming-indicator generation are disclosed. Friendly names for accessory devices, such as smart-home devices, may be utilized to generate formatted text data that includes capitalization and/or punctuation for the friendly names. The formatted text data may be utilized to generate tag data indicating attributes of the friendly name. The tag data and/or contextual data indicating historical usage of the accessory device may be utilized to generate naming indicator(s) for the accessory device. The naming indicator(s) may be utilized, for example, during target inference and/or for communicating with a user about the accessory device.

Abstract: The description relates to systems and methods for extending applications. For example, a voice assistant application can be the application to be extended. In an example, a mobile banking application can be the application that provides the extension. For example, a voice assistant might not have capability to conduct fingerprint (or biometric) authentication and bill payment function. An extension point within the voice assistant application that would enable this kind of capability might not exist. The mobile banking application can have a biometric tool for fingerprint authentication capability and a payment tool for a bill payment or money transfer function. Embodiments described herein can involve a deep link from the voice assistant application to the mobile banking application (which does offer fingerprint authentication and bill payment capability). The navigation to the mobile banking application can generate a visual impression at the UI similar or consistent with the voice assistant application.

Abstract: It is an object of the present invention to prevent inattentive listening to a dialogue of an agent without taking it seriously and to make it easier to understand the dialogue with the agent. A dialogue system 100 conducts a dialogue with a user 101. A humanoid robot 50-1 presents a leap-in-logic utterance, which is an utterance, of which a logical structure is partially missing. The user 101 expresses a confirmation action which is an action confirming the missing information in the leap-in-logic utterance. The humanoid robot 50-1 presents a supplementary utterance which is an utterance describing the missing information.

Abstract: In some aspects, an order post detects, using one or more sensors, a presence of a customer, determines an identity of the customer, retrieves previous orders of the customer, indicates at least one item in the previous orders, receives an order comprising input that includes an utterance of the customer, modifies the utterance to create a modified utterance, sends the modified utterance to a software agent comprising a natural language processor and one or more classifiers, receives a predicted response to the modified utterance from the software agent, plays back the predicted response via the speaker, determines that the order is complete, receives payment information for the order from the customer, sends order data associated with the order to a restaurant, receives an indication from the restaurant that the order is ready for pickup, and instructs the customer to pick up the order.

Abstract: Certain aspects of the present disclosure provide techniques for selecting a response to a self-support query. One example method generally includes receiving an audio stream query including spoken content from a user recorded by a mobile device and determining a set of paralinguistic features from the spoken content. The method further includes estimating an emotional state of the user based on the set of paralinguistic features and identifying subject matter of the spoken content in the audio stream query. The method further includes determining two or more query responses corresponding to the subject matter to present to the user and transmitting at least one query response to the mobile device.

Abstract: The present disclosure discloses a method for generating a styled sentence by a computer device. The method includes: obtaining a to-be-converted natural sentence, inputting the natural sentence into a first encoding model to filter style information in the natural sentence, and generating a target content vector corresponding to the natural sentence. The method also include determining, from at least one style vector according to a set target language style, a target style vector corresponding to the target language style; and inputting the target content vector and the target style vector into a first decoding model, and generating a styled sentence corresponding to the natural sentence.

Abstract: Many portable playback devices cannot decode and playback encoded audio content having wide bandwidth and wide dynamic range with consistent loudness and intelligibility unless the encoded audio content has been prepared specially for these devices. This problem can be overcome by including with the encoded content some metadata that specifies a suitable dynamic range compression profile by either absolute values or differential values relative to another known compression profile. A playback device may also adaptively apply gain and limiting to the playback audio. Implementations in encoders, in transcoders and in decoders are disclosed.

Abstract: A computing device includes a processor and a memory. The processor is configured to acquire a voice instruction through at least two voice receiving devices, analyze the voice instruction to determine at least one display device controlled by the voice instruction, generate a control instruction according to the voice instruction, and send the control instruction to the at least one display device to cause the at least one display device to display corresponding contents according to the voice instruction.

Abstract: An electronic device and a method for controlling the electronic device is provided. The electronic device includes a microphone, a memory configured to include at least one instruction, and a processor configured to execute the at least one instruction. The processor is configured to control the electronic device to perform voice recognition for an inquiry based on receiving input of a user inquiry through the microphone, and acquire a text for the inquiry, generate a plurality of inquiries for acquiring response data for the inquiry from a plurality of databases using a relation graph indicating a relation between the acquired text and data stored in the plurality of databases, acquire response data corresponding to each of the plurality of inquiries from each of the plurality of databases, and generate a response for the inquiry based on the response data acquired from each of the plurality of databases and output the response.

Abstract: A rear display displays a driver image of a driver to a rear occupant. An operational information acquisition unit acquires operational information for changing a size of the driver image displayed on the rear display. An image control unit changes the size of the driver image displayed on the rear display, on the basis of the operational information acquired by the operational information acquisition unit. A sound control unit controls, at a time of generating a synthetic sound by combining a spoken voice of the driver with a reproduced sound of an AV source, a sound-level ratio between the spoken voice of the driver and the reproduced sound of the AV source, on the basis of the size of the driver image displayed on the rear display. A rear speaker outputs the synthetic sound generated by the sound control unit toward the rear occupant.

Abstract: Fragment recall and adaptive automated translation are disclosed herein. An example method includes determining that an exact or fuzzy match for a portion of a source input cannot be found in a translation memory, performing fragment recall by matching subsegments in the portion against one or more whole translation units stored in the translation memory, and matching subsegments in the portion against corresponding one or more subsegments inside the one or more matching whole translation units, and returning any of the one or more matching whole translation units and the one or more matching subsegments as a fuzzy match, as well as the translations of those subsegments.

Abstract: An embodiment of a summarization application divides collected conversation data into media and text components. The application implements respective machine learning mechanisms to enhance modeling operations of the text and media components to identify key elements from the conversation. The application generates a headline banner from a group of key elements based on an analysis involving first predetermined criteria. The application also combines additional key elements to the group of key elements to form a second group of key elements. The application generates a summary from the second group of key elements based on a second analysis involving second predetermined criteria. The application presents, via a display, the headline banner according to a first output of the first key element analysis and the summary according to a second output of the second key element analysis.

Abstract: A hypernym of a word in utterance data may be probabilistically determined. The utterance data may correspond to a spoken query or command. A redacted utterance may be derived by replacing the word with the hypernym. The hypernym may be determined by applying noise to a position in a hierarchical embedding that corresponds to the word. The word may be identified as being potentially sensitive. The hierarchical embedding may be a Hyperbolic embedding that may indicate hierarchical relationships between individual words of a corpus of words, such as “red” is a “color” or “Austin” is in “Texas.” Noise may be applied by obtaining a first value in Euclidean space based on a second value in Hyperbolic space, and obtaining a third value in Hyperbolic space based on the first value in Euclidean space. The second value in Hyperbolic space may correspond to the word.

Abstract: An electronic apparatus is provided. The electronic apparatus includes a communicator, a memory, and a processor connected to the communicator and the memory and configured to control the electronic apparatus. The processor is configured to, by executing at least one command stored in the memory, based on a user input for executing an assistant service being received, transmit information on a user voice acquired by the electronic apparatus to a plurality of servers providing different assistant services through the communicator, and based on a plurality of response information being received from the plurality of servers, provide a response on the user voice based on at least one of the plurality of response information. The plurality of servers provide the assistant service using an artificial intelligence agent.