Abstract: A dialogue processing method and device are provided. The method includes: A dialogue processing device receives dialogue information from user equipment; if the dialogue information does not include slot information that is corresponding to a first slot type and that can determine a service, the dialogue processing device obtains a service identifier set corresponding to the first slot type from a server, and sends the service identifier set to the user equipment; and after a target service identifier is received from the user equipment, the dialogue processing device requests a service corresponding to the target service identifier from the server, and sends execution success information to the user equipment. According to this method, a service item can be presented to a user in a timely manner, and the user can be prevented from initiating a plurality of rounds of dialogues with the dialogue processing device, thereby improving service execution efficiency and further improving use experience of the user.

Abstract: An apparatus, system, method, and computer-readable recording medium for automatic routing of an audio output using a smart media device (SMD), which includes receiving a request for audio content or audio and visual content, obtaining the audio content or the audio and visual content requested, and determining a power state of an audio/video (AV) output device. If the power state is determined to be ON, the audio content or the audio and visual content is automatically routed to the AV output device, and if the power state is determined to be OFF, the audio content is automatically routed to the SMD for output. If the power state is determined to be OFF and the request is for audio and visual content, the power state of the AV output device is controlled ON, and the audio and visual content is routed to the AV output device.

Abstract: Various embodiments of the disclosure provide an electronic device and a method of operating the same, the electronic device including: a speech recognition module; a memory configured to store information corresponding to a plurality of domains related to a collaborative task; and a processor operatively connected to the speech recognition module or the memory, wherein the processor is configured to receive a user voice from a user, analyze the received user voice using the speech recognition module to determine whether or not to perform a collaborative task, if the collaborative task is determined to be performed, select at least one participant related to the collaborative task, collect information related to the collaborative task from the user or an electronic device of the selected participant, and perform the collaborative task, based on the collected information. Various embodiments may be provided.

Abstract: A technique is provided that can reduce degradation of the sound quality due to a tandem connection of paired coding and decoding, and can reduce the operation processing amount and the required memory amount of a multipoint control unit. In multipoint connection between terminals of a plurality of communication networks (for example, a fixed phone line and a mobile phone line) having different communication capacities, when a multichannel coding including a monaural coding scheme of a communication network having a smaller communication capacity is used in a communication network having a larger communication capacity to transmit sounds of a plurality points to the communication network terminal having the larger communication capacity, control is exercised such that monaural codes of the plurality points are output.

Abstract: This disclosure provides a loudspeaker, including a first basket; a second basket; a cone paper enclosing an accommodating cavity with openings at both ends, the openings at both ends of the cone paper being respectively provided with the first basket and the second basket; a magnetic circuit structure located in the accommodating cavity; and a voice coil assembly located in the accommodating cavity, installed between the magnetic circuit structure and an inner wall of the accommodating cavity of the cone paper, and connected to the inner wall of the accommodating cavity of the cone paper, the voice coil assembly being configured to move under an action of a magnetic field of the magnetic circuit structure to drive the cone paper to vibrate. This disclosure further provides a loudspeaker device.

Abstract: An acoustic event detection system may employ one or more recurrent neural networks (RNNs) to extract features from audio data, and use the extracted features to determine the presence of an acoustic event. The system may use self-attention to emphasize features extracted from portions of audio data that may include features more useful for detecting acoustic events. The system may perform self-attention in an iterative manner to reduce the amount of memory used to store hidden states of the RNN while processing successive portions of the audio data. The system may process the portions of the audio data using the RNN to generate a hidden state for each portion. The system may calculate an interim embedding for each hidden state. An interim embedding calculated for the last hidden state may be normalized to determine a final embedding representing features extracted from the input data by the RNN.

Abstract: A sounding device a normal speaker being configured to output a first sound, a bone conduction speaker being configured to output a second sound, a storage unit being configured to store first and second data corresponding to the first and second sounds respectively, and an output control unit being configured to control outputting the first sound from the normal speaker and the second sound from the bone conduction speaker. The first sound is of talking. The second sound is of a pet. The output control unit is configured to control the bone conduction speaker to output the first sound, and to control the normal speaker to output the second sound.

Abstract: A device and method for generating article markup information are provided. The method for generating article markup information includes the following. Segmentation processing is performed on an article to generate a segmentation result. Name entity recognition is performed on the segmentation result to generate a first recognition result. Whether the segmentation result includes any word in an expansion list is determined. Expanded entity classification conversion is performed on the first recognition result to generate a second recognition result. The second recognition result and the segmentation result are used as markup information.

Abstract: Wireless-enabled loudspeaker includes a wooden capacitive touch user interface. The loudspeaker may comprise at least one electroacoustic transducer, a processor in communication with the at least one electroacoustic transducer, and a wooden exterior surface comprising a capacitive touch user interface that allows a user to control operation of the loudspeaker. The wooden exterior surface acts a dielectric for the capacitive touch user interface. The loudspeaker may comprise a wireless transceiver circuit for receiving and transmitting wireless communication signals via a wireless network. The wireless transceiver circuit may receive wirelessly audio content from streaming audio content servers that are connected to the Internet. The capacitive touch user interface comprises a plurality of user control icons etched in the wooden exterior surface, and a plurality of capacitive sense electrodes located under the wooden exterior surface.

Abstract: Audio device, electronic circuit, and related methods, in particular a method of manufacturing an electronic circuit for an audio device is disclosed, the method comprising providing a circuit board; mounting one or more electronic components including a first electronic component on the circuit board; applying a first insulation layer outside the first electronic component; and applying a first shielding layer outside the first insulation layer.

Abstract: An actuator for exciting a component of a motor vehicle with vibrations. The actuator has a housing, an electrical coil and a magnet that is movable to a limited extent in the housing.

Abstract: The signal separation device includes: cross product calculation means receiving an input of an observed signal that is a mixture of a plurality of target signals, and calculating a cross product of the observed signal; model calculation means updating a parameter of a model for estimating the cross product with a predetermined algorithm using an inverse matrix of a matrix that represents an estimate of the cross product; inverse matrix calculation means calculating the inverse matrix of a matrix by a SIMD command when the parameter is updated; and separation means calculating the target signals using a matrix representing an estimate of the cross product, the updated parameter, and the observed signal.

Abstract: According to an embodiment of the disclosure, an electronic device may include a speaker, a microphone, a wireless communication circuit, and at least one processor connected to the speaker, the microphone, and the wireless communication circuit. The at least one processor may be configured to: in response to a user's voice command received through the microphone, perform a task corresponding to the voice command, based on an information amount contained in a result of the task, determine a type of the result to be visually appropriate or auditorily appropriate, and based on the type of the result, determine a device for providing the result as a screen device or a speaker.

Abstract: Disclosed is a system, a hearing device and a method for encapsulating one or more electronic components on a substrate. The method comprises providing a dam on the substrate, the dam is provided around the one or more electronic components, the dam comprises a dam material comprising an electrically conducting material. The method comprises providing a liquid fill encapsulation material within the dam on the substrate, the fill encapsulation material encapsulates the one or more electronic components, the fill encapsulation material is configured to solidify, the solidified fill encapsulating material comprises a first surface exposed to surroundings. The method comprises applying a cover material on the first surface of the solidified fill encapsulation material, the cover material comprising an electrically conducting material, whereby the one or more electronic components are encapsulated and electromagnetically shielded.

Abstract: Systems for voice control of medical devices in a healthcare facility are disclosed herein. The systems employ continuous speech processing software, voice recognition software, natural language processing software, and other software to permit voice control of the medical devices. Systems are also provided for distinguishing which medical device from among multiple medical devices in a patient room is the particular medical device to be controlled by voice input from a caregiver or a patient.

Abstract: There are two representations for Higher Order Ambisonics denoted HOA: spatial domain and coefficient domain. The invention generates from a coefficient domain representation a mixed spatial/coefficient domain representation, wherein the number of said HOA signals can be variable. An aspect of the invention further relates to methods and apparatus decoding multiplexed and perceptually encoded HOA signals, including transforming a vector of PCM encoded spatial domain signals of the HOA representation to a corresponding vector of coefficient domain signals by multiplying the vector of PCM encoded spatial domain signals with a transform matrix and de-normalizing the vector of PCM encoded and normalized coefficient domain signals, wherein said de-normalizing comprises.

Abstract: A speech-controlled vanity mirror is provided, which includes a vanity mirror body, a first microphone, a second microphone and a speech recognition control device provided on the vanity mirror body. The speech recognition control device includes a music control device and a speech control device. The first microphone is connected to the music control device, and transmits the audio signal acquired from a loudspeaker to the music control device. A filter in the music control device filters the audio signal to eliminate the interference of the audio played by the loudspeaker in speech instructions of the user. The second microphone is connected to the speech control device, and transmits the speech instructions of the user to the speech control device. The speech control device adjusts and controls a multifunctional device on the vanity mirror body according to the speech instructions. It is convenient for users to operate, and the recognition rate and accuracy of the speech instruction are high.

Abstract: Systems and methods for distinguishing valid voice commands from false voice commands in an interactive media guidance application. In some aspects, the interactive media guidance application receives, at a user device, a signature sound sequence. The interactive media guidance application determines, using control circuitry, based on the signature sound sequence, a threshold gain for the current location of the user device. The interactive media guidance application receives, at the user device, a voice command. The interactive media guidance application determines, using the control circuitry, based on the voice command, a gain for the voice command. The interactive media guidance application determines, using the control circuitry, whether the gain for the voice command is different from the threshold gain. Based on determining that the gain for the voice command is different from the threshold gain, the interactive media guidance application executes, using the control circuitry, the voice command.

Abstract: A smart mask includes a main body having a back frame and a front cover. The back frame and the front cover each include an opening that is aligned with the mask wearer's mouth when worn. The front cover and back frame may be detachable from one another, or a single piece. A microphone is provided in the main body, as well as a speaker. A processor located in the main body is connected to the microphone and the speaker, and is configured to enhance the speech of the mask wearer. In particular, the processor receives audio signals representing a transformation of a spoken utterance of the wearer, processes the audio signals to enhance the speech, and then outputs the enhanced speech to the speaker. This helps other people better understand what the mask wearer is saying.

Abstract: Methods and apparatus for harmonic source enhancement are disclosed herein. An example apparatus includes an interface to receive a media signal. The example apparatus also includes a harmonic source enhancer to determine a magnitude spectrogram of audio corresponding to the media signal; generate a time-frequency mask based on the magnitude spectrogram; and apply the time-frequency mask to the magnitude spectrogram to enhance a harmonic source of the media signal.