Abstract: An apparatus comprising means configured to: receive a primary track comprising at least one audio signal; receive at least one secondary track, each of the at least one secondary track comprising at least one audio signal, wherein the at least one secondary track is based on the primary track; and decode and render the primary track and the at least one secondary track using spatial audio decoding.

Abstract: Techniques for detecting certain acoustic events from audio data are described. A system may perform event aggregation for certain types of events before sending an output to a device representing the event is detected. The system may bypass the event aggregation process for certain types of events that the system may detect with a high level of confidence. In such cases, the system may send an output to the device when the event is detected. The system may be used to detect acoustic events representing presence of a person or other harmful circumstances (such as, fire, smoke, etc.) in a home, an office, a store, or other types of indoor settings.

Abstract: A system, method, and computer program are provided for text sanitization. The system builds a corpus of document vectors (including tokenizing each document, creating a vector representation based on the tokens, and building a corpus of vector representations), obtains a new document for text sanitization, tokenizes the new document, creates a new document vector based on the tokens in the new document, and accesses the corpus of document vectors. The system filters each of the tokens in the new document against a privacy threshold. The system performs a k-anonymity sanitization process such that the new document vector becomes indistinguishable from at least k other document vectors in the corpus of document vectors. The system replaces or redacts the tokens in the document flagged as unsafe. The system updates the corpus of document vectors to include the new document vector in its form prior to the filtering and k-anonymity sanitization steps.

Abstract: An electronic device is provided. The electronic device includes a communication module, a sensor module, a sound input module, a sound output module, a memory including a buffer, and a processor.

Abstract: A method for estimating the aging of an electronic component, characterized in that it includes the following steps: —compiling a thermal specification of the electronic component in order to determine a reference lifetime, —determining a reference temperature quantity, —measuring the actual temperature of the electronic component in operation, —determining an actual temperature quantity, —determining an equivalent operating time at the actual temperature, —transposing this equivalent operating time to the reference temperature to obtain a transposed operating time, —summing the transposed operating times to obtain a consumed lifetime comparable to the reference lifetime.

Abstract: An occupancy tracking device configured to receive a plurality of sound samples over a predetermined time period. The device is further configured to compute an audio signature for each sound sample. The device is further configured to populate entries in the voice data log for the sound samples, to identify one or more clusters based on an audio signature that is associated with the populated entries, and to determine a number of clusters that are identified. The device is further configured to determine a predicted occupancy level based on the number of clusters that are identified and to control a Heating, Ventilation, and Air Conditioning (HVAC) system based on the predicted occupancy level.

Abstract: An audio coding method and apparatus are provided. The audio coding method includes: obtaining first audio data; obtaining a target bit rate and a Bluetooth packet type, where the target bit rate and the Bluetooth packet type correspond to a current status of a Bluetooth channel; obtaining one or more of a bit pool parameter set, a psychoacoustic parameter set, and a spectrum bandwidth parameter set by using a neural network obtained through pre-training based on the first audio data, the target bit rate, and the Bluetooth packet type; and coding the first audio data based on one or more of the bit pool parameter set, the psychoacoustic parameter set, and the spectrum bandwidth parameter set to obtain a to-be-sent bit stream. The status of the Bluetooth channel can be adaptively matched, and continuous audio listening experience is provided when audio quality is maximally ensured.

Abstract: A method of authorizing content for use, e.g., in association with a conversational bot. The method begins by configuring a conversational bot using a machine learning model trained to classify utterances into topics. Utterances that are not recognized by the machine learning model (e.g., according to some configurable threshold) are then identified. Using a clustering algorithm, one or more of the identified utterances are then processed into a grouping. Information identifying a topic associated with the grouping is then received and, in response, the machine learning model is updated to include the topic.

Abstract: This application relates to an audio synthesis method, a storage medium, and a computer device. The method includes: obtaining a target text; determining a target song according to a selection instruction; synthesizing a self-made song using the target text and tune information of the target song according to a tune control model, the target text being used as the lyrics of the self-made song. The solutions provided in this application improve an audio playback effect.

Abstract: Methods and systems are provided for detecting artifacts in an electronic signal. In an embodiment, a method is provided comprising: connecting a first input of an electronic device to a first signal line of a signal processing device, such as an amplification device; connecting a second input of the electronic device to a second signal line of the signal processing device, the second signal line being downstream from the first signal line; establishing, based on an observed behavior of a first signal on the first signal line, an expected behavior of a second signal on the second signal line; and determining whether a difference exists between the expected behavior of the second signal and an observed behavior of the second signal. If a difference is detected, the expected behavior of a second signal and the observed behavior of the second signal may be recorded for later analysis.

Abstract: The invention provides a content playback system comprising a playback device that is configured to detect a voice command from a user and to play content. When a voice command is received, the system is configured to analyse the voice command to determine a user intent. The system then extracts one or more entities from the voice command, wherein each of the extracted entities is of a type associated with the determined user intent. Then, based on the one or more extracted entities, the system controls the playback device. Analysis of the voice command in this manner may improve an accuracy with which a meaning of the voice command can be obtained, thereby facilitating control of the playback device.

Abstract: The approach disclosed herein is a new approach to sequence generation in the context of validation that relies on machine learning to explore and identify ways to achieve different states. In particular, the approach uses machine learning models to identify different states and ways to transition from one state to another. Actions are selected by machine learning models as they are being trained using reinforcement learning. This online inference also is likely to result in the discovery of not yet discovered states. Each state that has been identified is then used as a target to train a respective machine learning model. As part of this process a representation of all the states and actions or sequences of actions executed to reach those states is created. This representation, the respective machine learning models, or a combination thereof can then be used to generate different test sequences.

Abstract: Techniques are described herein for concurrent voice assistants. A method includes: providing first and second automated assistants with access to one or more microphones; receiving, from the first automated assistant, an indication that the first automated assistant has initiated a first session, and in response: continuing providing, to the first automated assistant, access to the one or more microphones; discontinuing providing, to the second automated assistant, access to the one or more microphones; and preventing the second automated assistant from accessing one or more portions of an output audio data stream; receiving, from the first automated assistant, an indication that the first session has ended, and in response: continuing providing, to the first automated assistant, access to the one or more microphones; resuming providing, to the second automated assistant, access to the one or more microphones; and resuming providing, to the second automated assistant, the output audio data stream.

Abstract: An apparatus for determining the volume of fluid dispensed. The apparatus has an acoustic volume sensor that acoustically excites a reference volume and a measurement chamber with a loudspeaker and measures the acoustic response with microphones acoustically coupled to the reference and the measurement chamber. The loudspeaker and sensing microphones are connected to the measurement chamber by separate ports. A detachable dispensing chamber is coupled to the acoustic volume sensor. The volume of the fluid dispensed is determined by a processor based on the acoustic response of the microphones to acoustic excitement by the loudspeaker.

Abstract: The system provides a voice command recommendation to a user to avoid a non-voice command. The system determines a command that is expected to be received, and generates a voice command recommendation that corresponds to the predicted command. The predicted command can be based on the user's behavior, a plurality of users' behavior, environmental circumstances such as a phone call ring, or a combination thereof. The system may access one or more databases to determine the predicted command. The voice command recommendation may include a displayed notification that describes the recommended voice command, and exemplary voice inputs that are recognized. The system also activates an audio interface, such as a microphone, that is configured to receive a voice input. If the system receives a recognizable voice input at the audio interface that corresponds to the recommendation, the system performs the predicted command in response to receiving the voice input.

Abstract: Pages describing episodes of podcasts or other media entities are constructed by interpreting content of the media entities. A transcript of an episode is determined by one or more natural language understanding techniques and divided into chapters. For each of the chapters, a summary sentence of the chapter and one or more key phrases are determined from the transcript, and participants in the chapter are identified. A summary of the episode is determined from the summary sentences of each of the chapters. A page that describes the episode of the podcast including the summary of the episode, as well as one or more of the key phrases and identities of the participants is generated and provided to prospective listeners to the episode.

Abstract: A method includes receiving audio stream data associated with a data capture environment, and receiving sensor data associated with the data capture environment. The method also includes identifying at least some events in the sensor data, and calculating at least one offset value for at least a portion of the audio stream data that corresponds to at least one event of the sensor data. The method also includes synchronizing at least a portion of the sensor data associated with the portion of the audio stream data that corresponds to the at least one event of the sensor data, and labeling at least the portion of the audio stream data that corresponds to the at least one event of the sensor data. The method also includes generating training data using at least some of the labeled portion of the audio stream data, and training a machine learning model using the training data.

Abstract: The computing system trains an end-to-end (E2E) automatic speech recognition (ASR) model, using a transformer-transducer-based deep neural network that comprises a transformer encoder network and a transducer predictor network. The E2E ASR model is trained to have one or more adjustable hyperparameters that are configured to dynamically adjust an efficiency or a performance of the E2E ASR model when the E2E ASR model is deployed onto a device or executed by the device, by identifying one or more conditions of the device associated with computational power of the device and setting at least one of the one or more adjustable hyperparameters based on one or more conditions of the device.

Abstract: Systems and methods for managing conversations between a robot computing device and a user are disclosed. Exemplary implementations may: initiate a first-time user experience sequence with the user; teach the user the robot computing capabilities and/or characteristics; initiate, utilizing a dialog manager, a conversation with the user; receive, one or more command files from the user via one or more microphones; and generate conversation response files and communicating the generated conversation files to the dialog manager in response to the one or more received user global command files to initiate an initial conversation exchange.

Abstract: A method for comprehensively analyzing and/or evaluating cigarette burning quality index is disclosed. The steps include collecting cigarette burning quality index data, filtering the cigarette burning quality index data, standardizing cigarette data, and measuring cigarette burning quality. The importance of the cigarette burning quality indicators can also be evaluated. The method for comprehensively analyzing and/or evaluating cigarette burning quality indicators can reflect general laws more accurately by maintaining the sample distribution through a singularity detection method, and analyzing correlations of each index with cigarette performance from multiple perspectives, to fuse them into a comprehensive measurement value. The importance ranking and weight of indicators can be obtained more completely and stably.