Abstract: Embodiments of an adaptive virtual intelligent agent (“AVIA”) service are disclosed. It may include the functions of a human administrative assistant for an enterprise including customer support, customer relationship management, and fielding incoming caller inquiries. It also has multi-modal applications for the home through interaction with AVIA implemented in the home. It may engage in free-form natural language dialogs. During a dialog, embodiments maintain the context and meaning of the ongoing dialog and provides information and services as needed by the domain of the application. Over time, the service automatically extends its knowledge of the domain (as represented in the Knowledge Tree Graphs) through interaction with external resources.

Abstract: Methods and devices for establishing a communication between a first and a second terminal are described. The disclosed technology can be implemented in or by a server or a terminal in communication with the server. The first terminal can to the server, using a first calling identity, a request including connection information and an identifier of the first terminal. Using the identifier, the server can obtain from a database a pair of calling identities including one certified and one non-certified, the pair comprising the first calling identity and a second calling identity. The server can determine, from one of the calling identities and from the connection information, a connectivity mode of the terminal, and determine a routable number on which the terminal can send a communication to the server. The server can route the communication towards the second terminal by presenting a calling identity of the pair and sending the routable number to the first terminal.

Abstract: Technology for identifying that a communication is from a verified enterprise includes receiving, by a device associated with a user, a data packet from a phone network. The data packet can be included in a communication to the device, which can have an application configured to verify communications from at least one enterprise. A token within the data packet can be identified by the application, and the application can compare the token to at least one token identifier associated with the at least one enterprise. In response to the token corresponding to at least one token identifier, the application can verify that the communication is from the at least one enterprise. In response to the communication being verified, the application can display a validation image on the device.

Abstract: A loudspeaker device comprising a loudspeaker unit comprising a diaphragm with a first and second surface (such as the front and rear surface of the diaphragm, respectively) and an enclosure in which the loudspeaker unit is mounted such that the first surface of the diaphragm is in acoustic communication with the surroundings of the loudspeaker device. The device further comprises an internal cavity formed in the enclosure and being in acoustic communication with the surroundings of the loudspeaker device via an acoustic element. In the device, the second surface of the diaphragm is in acoustic communication with the internal cavity. The acoustic element can be varied between a state in which sound energy generated by the loudspeaker unit in the internal cavity can be emitted to the surroundings via the acoustic element and a state in which sound energy is substantially prevented from entering the surroundings via the acoustic element.

Abstract: An indoor target positioning method based on an improved convolutional neural network (CNN) model includes acquiring and preprocessing target camera serial interface (CSI) data of a to-be-positioned target and matching the preprocessed target CSI data with fingerprints in a positioning fingerprint database to obtain coordinate information of the to-be-positioned target. The generation method of the positioning fingerprint database includes: collecting indoor WiFi signals by a software defined radio (SDR) platform to obtain indoor CSI data corresponding to the WiFi signals, and preprocessing the indoor CSI data; partitioning the preprocessed indoor CSI data into a plurality of data subsets through a clustering algorithm; training an improved CNN model by the data subsets to obtain a trained improved CNN model; and generating the positioning fingerprint database by the trained improved CNN model and the preprocessed indoor CSI data.

Abstract: A method of multi-talker separation using a 3-tuple coprime microphone array, including generating, by a subarray signal processing module, a respective subarray data set for each microphone subarray of the 3-tuple coprime microphone array based, at least in part, on an input acoustic signal comprising at least one speech signal. The input acoustic signal is captured by the 3-tuple coprime microphone array. The 3-tuple coprime microphone array includes three microphone subarrays. The method includes determining, by the subarray signal processing module, a point by point product of the three subarray data sets; and determining, by the subarray signal processing module, a cube root of the point by point product to yield an acoustic signal output data. The acoustic signal output data has an output amplitude and an output phase corresponding to an input amplitude and an input phase of a selected speech signal of the at least one speech signal.

Abstract: An unistructurally formed acoustic speaker cone unit includes (a) a suspension ring with at least one continuous loop rib; (b) a central dome-shaped cone with thin, arcuate pie-shaped segments which radiate outwardly, and with a plurality of arc ribs; and (c) a main diaphragm having a plurality of segments radiating outwardly and extending to the suspension ring. Each main diaphragm segment has an arcuate cross-section, thereby creating a concave side and a convex side. The central cone segments are preferably equal in number to the diaphragm segments and are in alignment therewith.

Abstract: An enhanced routing system determines a service provider best suited to fulfill a user's request to interact and establishes a communication session between the user's client device and a device of the service provider. The enhanced routing system may use user characteristics and behavior to select the service provider. For example, the enhanced routing system receives a request to connect to a customer service system from a user who has recently started a new job and has been accessing a banking application on his mobile phone. The enhanced routing system may determine that a payroll service provider is best suited to fulfill the user's request. For example, the enhanced routing system uses a machine learning model that has been trained on previously fulfilled requests. In this way, the enhanced routing system improves upon systems that continuously prompt the user for information by selecting a service provider without overburdening the user.

Abstract: A method is provided. The method comprises a computer performing receiving notice of an incoming inquiry originated by a customer device. The method further comprises the computer performing instantiating a session with the customer device, the session performing comprising the computer combining chatbot functionality and flow control functionality. The method further comprises the computer performing a prompt to the customer device, the prompt comprising a set of valid selections. The method further comprises the computer performing receiving a selection from the customer device. The method further comprises the computer, performing based on the received selection, at least one of providing information to the customer device and routing the inquiry.

Abstract: Systems and methods of providing policy and charging control in an information-centric network are described. An interest packet is transmitted from a content consumer to a holder through a gNB, ICN-PoA and ICN-GW. The interest packet has a prefix identifying content to be retrieved and a type field indicating an interest packet. The ICN-PoA modifies the interest packet to include a type of service (TS) field having the identity of the consumer and then transmitted to the ICN-GW when the content is neither created nor cached inside the 5G network. A data packet that includes the prefix, a type field indicating a data packet and the TS field is returned from the ICN-GW. The data packet is modified by the ICN-PoA to remove the TS field and transmitted to the consumer. The interest and data packets are logged and reported to an ICN-CF for generation of charging records.

Abstract: In one embodiment, a device obtains call transcripts from an online application. The device detects cues within the call transcripts that are indicative of poor user experience. The device generates, based in part on the cues detected within the call transcripts, a model trained to predict poor user experience from network path telemetry for the online application. The device causes traffic for the online application to be routed along a particular network path, based on a prediction by the model.

Abstract: A method for generating loudspeaker signals associated with a target screen size is disclosed. The method includes receiving a bit stream containing encoded higher order ambisonics signals, the encoded higher order ambisonics signals describing a sound field associated with a production screen size. The method further includes decoding the encoded higher order ambisonics signals to obtain a first set of decoded higher order ambisonics signals representing dominant components of the sound field and a second set of decoded higher order ambisonics signals representing ambient components of the sound field. The method also includes combining the first set of decoded higher order ambisonics signals and the second set of decoded higher order ambisonics signals to produce a combined set of decoded higher order ambisonics signals.

Abstract: A rear side of a vibration part of a speaker is covered by a cover member, and a duct is provided at the cover member. The cover member has a recessed portion, and an air flow path is formed inside the recessed portion. A circuit part is mounted on an outer surface of the cover member, and a heat sink provided in the air flow path is connected to the circuit part to allow heat conduction. Due to vibration of the vibration part, an airflow in the air flow path is accelerated and thus the effect of dissipating heat from the heat sink is increased.

Abstract: Systems and methods for categorizing received calls based on early call information are disclosed. Early call information can be audio, video, other sensor data, or other data collected via a calling device during call setup or any time before the call is routed to or accepted at a receiving device. A call and early call information associated with the call are received. A call characteristic, which can be a purpose or topic of the call, is identified using the early call information. Based on the call characteristic, the received call is categorized and a relative priority for the call is assigned. The call can be routed based on the early call information, and a suggested response to the call can be identified. In some implementations, a machine learning model is trained to categorize received calls based on early call information.

Abstract: A stereo encoding method and apparatus, and a stereo decoding method and apparatus are disclosed. The stereo encoding method includes: performing downmix processing on a left channel signal of a current frame and a right channel signal of the current frame, to obtain a primary channel signal of the current frame and a secondary channel signal of the current frame; and when determining that a frame structure similarity value falls within a frame structure similarity interval, performing differential encoding on a pitch period of the secondary channel signal by using an estimated pitch period value of the primary channel signal, to obtain a pitch period index value of the secondary channel signal, where the pitch period index value of the secondary channel signal is used to generate a to-be-sent stereo encoded bitstream.

Abstract: Aspects of the subject disclosure may include, for example, detecting, over a network, a call originating from a call originator and intended for a user of a user equipment, responsive to the detecting the call, determining whether to challenge the call originator, based on a determination to challenge the call originator, transmitting a request to the call originator, wherein the request prompts the call originator to specify an identity of the call originator and a purpose for the call, obtaining information from a call originator input responsive to the transmitting the request, deriving enhanced Caller Name or Caller ID data that includes the information, and causing the enhanced Caller Name or Caller ID data to be provided to the user equipment, thereby enabling the user of the user equipment to determine whether to answer the call. Other embodiments are disclosed.

Abstract: Aspects of the present disclosure provide methods and apparatuses for determining a nozzle of an audio device is, at least partially blocked. More specifically, based on a measured transfer function between the driver and a microphone and an expected transfer function between the driver and the microphone, a blockage is detected. In response to the detected blockage, the user is notified.

Abstract: A transducer includes a base, beams, and a coupler. The beams each include a piezoelectric layer, a first electrode layer, and a second electrode layer. The coupler is fitted in slits between adjacent beams to define a connection between the beams. The coupler extends from an upper portion of the base into each of the slits without a break. A Young's modulus of the material of the coupler is lower than a Young's modulus of the material of the piezoelectric layer. A maximum thickness of the coupler in the upper portion of the base in the direction of the central axis of the base is greater than a thickness of each of the beams.

Abstract: An electrodynamic actuator for a speaker or an electrodynamic acoustic transducer in general is disclosed, which comprises at least one voice coil, a magnet system and an arm arrangement of a plurality of arms connecting the at least one voice coil and the magnet system or at least a movable part thereof so that a relative movement between these parts is allowed. The arms are made of a metal core, which at least partly is coated with a coating structure having at least one coating metal layer consisting of a different material than the metal core.

Abstract: An example operation may include one or more of receiving, via a telephone network, a Voice over IP (VOIP) call from a network device, detecting a disturbance value from a tag that has been added to a VOIP message of the VOIP call, determining an answer priority of the VOIP call based on the disturbance value, and processing the VOIP call based on the determined answer priority.