Abstract: The system allows a consumer to shortcut through a call queue to reach a human agent faster. For phone or voice-based calls that require a consumer wait on hold, the system can give that consumer an accurate estimate of the wait time and allow them to skip all or some of it. It does this by using automated processes to proactively dial and wait in those call queues, measuring their time in queue. A new consumer making an incoming call can then join the call queue occupied by of those automated processes, shortcutting the consumer past all or some of the wait time.

Abstract: A panel vibration type sound generating display device is disclosed. The display device includes a display panel for displaying an image; a sound generating actuator connected to the display panel and configured to vibrate the display panel to generate sound; a support structure spaced apart from the display panel with an air gap between the support structure and the display panel; and a baffle part disposed between the support structure and the display panel to surround the air gap.

Abstract: Techniques are described for generating a custom voice for a virtual agent. In one implementations, a method includes receiving information identifying a customer contacting a call center. The method includes selecting a voice for a virtual agent based on information about the customer. The method also includes assigning the voice to the virtual agent during communications with the customer.

Abstract: A multi-line digital transceiver configured to use digital signal vectoring in a manner that causes effects of crosstalk between distinct groups of subscriber lines to be effectively mitigated, without directly attempting to mitigate effects of crosstalk within any one of those distinct groups. In an example embodiment, effects of crosstalk within each of the distinct groups can be mitigated indirectly using an appropriate T/FDMA schedule, according to which, during a given symbol period, a given resource block of any of the distinct groups can carry data corresponding to a single respective subscriber. A precoder (postcoder) matrix for the digital signal vectoring can be generated using block-diagonalization techniques appropriately constrained, e.g., using the groups' definitions, aggregate-transmit-power restrictions, etc. In various embodiments, the disclosed digital signal vectoring can be used on the downlink or on the uplink, or both.

Abstract: Agencies issue recording devices to personnel for administrating and monitoring controlled calls during the course of their duties. To provide flexible capabilities to agencies, a virtual number is provisioned and configured to enable an operator to administrate controlled calls without dedicated recording devices. Using the virtual number, the operator may setup a controlled call between a victim and a baddie. The victim is contacted via the virtual number by the operator and optionally informed about the controlled call process. In turn, the baddie is contacted using number information of the victim's phone and connected with the victim. Call audio between the victim and baddie is transmitted to the operator. When necessary, the operator may terminate the call remotely from the telephonic device the operator used to setup the call.

Abstract: Each of plural dialogue devices generates proposition information that is an utterance indicating a proposition for passengers who are on board plural vehicles, based on an utterance submitted by a passenger and current destination information and past destination information. The dialogue device transmits the generated proposition information to other dialogue device.

Abstract: When a call session is set over an IP network between a calling IP phone and a called IP phone at the start of a call, information on the quality of communication between a host IP phone and a recording server is exchanged to compare the quality of communication of the two IP phones in each of the calling IP phone and the called IP phone. For example, the called IP phone, or a host IP phone, with a higher quality of communication than the calling IP phone of a conversing party transmits call audio data to the recording server as recording data. Meanwhile, the calling IP phone, or a host IP phone, with a lower quality of communication than the called IP phone of a conversing party refrains from transmitting the call audio data to the recording server.

Abstract: Systems and methods are provided for conducting conference calls using doppler-based, i.e., reverberation-based techniques. The embodiments comprise a call device performing operations to join a call session hosted on a session server; receive sensor data comprising an audio signal from a first microphone and location information associated with the first microphone; determine a reverberation parameter associated with the location information; generate a first processed audio signal based on the audio signal and the reverberation parameter; and transmit the first processed audio signal to the session server. The session server may perform operations to receive a respective processed audio signal; determine a sound quality parameter of the respective processed audio signal; generate a balanced audio signal based on the sound quality parameter and the received processed audio signal; and transmit the balanced audio signal to a remote call device belonging to a second party.

Abstract: Audio objects are associated with positional metadata. A received downmix signal comprises downmix channels that are linear combinations of one or more audio objects and are associated with respective positional locators. In a first aspect, the downmix signal, the positional metadata and frequency-dependent object gains are received. An audio object is reconstructed by applying the object gain to an upmix of the downmix signal in accordance with coefficients based on the positional metadata and the positional locators. In a second aspect, audio objects have been encoded together with at least one bed channel positioned at a positional locator of a corresponding downmix channel. The decoding system receives the downmix signal and the positional metadata of the audio objects. A bed channel is reconstructed by suppressing the content representing audio objects from the corresponding downmix channel on the basis of the positional locator of the corresponding downmix channel.

Abstract: A server can receive a plurality of records at a databases such that each record is associated with a phone call and includes at least one request generated based on a transcript of the phone call. The server can generate a training dataset based on the plurality of records. The server can further train a binary classification model using the training dataset. Next, the server can receive a live transcript of a phone call in progress. The server can generate at least one live request based on the live transcript using a natural language processing module of the server. The server can provide the at least one live request to the binary classification model as input to generate a prediction. Lastly, the server can transmit the prediction to an entity receiving the phone call in progress. The prediction can cause a transfer of the call to a chatbot.

Abstract: A method for communicating with a call center, is performed at a client device having one or more processors and memory. The client device establishes, via an instant messaging application running on the client device, a network session connection to the call center by using an audio and video server. The client device receives, through the network session connection, a first-level voice menu sent by the call center. The client device obtains a correspondence between visualized menus and voice menus of the call center. The device searches for a first visualized menu corresponding to the first-level voice menu according to the correspondence. The client device presents the first visualized menu in a user interface of the instant messaging application and plays information about an option in the first visualized menu in an on-demand voice manner in response to user input detected on the option in the user interface.

Abstract: A dialogue system and a vehicle having the same is provided. The dialogue system may recognize the user's speech, which is transmitted from the speech input device, as a text, derive user labeling context information after verifying an entity of the text, store the user labeling context information in the type to share an entity ontology with other user, and generate a dialogue response to perform an action corresponding when a user performs a free utterance or a designated entity utterance.

Abstract: An onboard control device includes: a deriving section that, on the basis of information that is an object of outputting, derives a conveying degree that expresses an extent to which it is desired to convey the information that is the object of outputting to each of plural occupants who exist within a vehicle; a selecting section that, in accordance with the conveying degrees of each of the vehicle occupants that have been derived by the deriving section, selects an outputting device that is to output the information that is the object of outputting, from among plural outputting devices that exist within the vehicle; and a control section that carries out control for causing the information, which is the object of outputting, to be outputted from the outputting device selected by the selecting section.

Abstract: An example method is described. The method includes receiving, by a computing system, data indicative of a call into an interactive voice response (IVR) system from a user device and determining, by the computing system and based on the data, a set of actions performed by the user device within the IVR system and a corresponding set of results performed by the IVR system during the call. Additionally, the method includes converting, by the computing system, the set of actions and the corresponding set of results into a sequence of code pairs using a dictionary established based on training data, determining, by the computing system, an activity pattern during the call based on the sequence of code pairs; and calculating, by the computing system, a probability that the call is fraudulent based on the activity pattern during the call.

Abstract: The present application provides a method of manufacturing a resonant panel (200) of a flat panel loudspeaker. The method comprises: pressing a resonant panel blank between a first pressing surface (302) and a second pressing surface of a press, whereby to form the resonant panel (200) of the flat panel loudspeaker. The second pressing surface substantially opposes the first pressing surface (302). The first pressing surface (302) comprises at least one tool relief region (306, 312, 314, 316, 318), whereby to form at least one corresponding respective panel relief region (206, 212, 214, 216, 218) in a surface of the resonant panel (200).

Abstract: Techniques are described for using stenography to protect sensitive information within conversational audio data by generating a pseudo-language representation of conversational audio data. In some implementations, audio data corresponding to an utterance is received. The audio data is classified as likely sensitive audio data. A particular set of sentiments associated with the audio data is determined. Data indicating the particular set of sentiments associated with the audio data is provided to a model. The model is trained to output, for each of different sets of sentiments, desensitized, pseudo-language audio data that exhibits the set of sentiments, and is not classified as likely sensitive audio data. A particular desensitized, pseudo-language audio data is received from the model. The audio data is replaced with the particular desensitized, pseudo-language audio data and stored within an audio data repository.

Abstract: A gaming device, during play of a particular game, receives a plurality of audio channels carrying game sounds and determines whether a first of the game sounds overwhelms a second of the game sounds. In response to the determination, the gaming device adjusts a level of one or more of the audio channels such that perceptibility of the second game sound is improved relative to perceptibility of the first game sound prior to the adjustment, wherein for the adjustment, a level of one or more of the audio channels carrying the first game sound is decreased while a level of one or more of the audio channels carrying the second game sound is maintained or increased. The audio channels include three or more audio channels and the adjustment of the level of the audio channels is performed while the three or more audio channels are combined into two stereo channels.

Abstract: Each of plural dialogue devices generates proposition information that is an utterance indicating a proposition for passengers who are on board plural vehicles, based on an utterance submitted by a passenger and current destination information and past destination information. The dialogue device transmits the generated proposition information to other dialogue device.

Abstract: A real-time messaging system platform receives from, a communication application installed on a first user communication device, a first user identifier, an indication that a messaging service message composed by the first user is being directed to a first destination associated with a second user, and an identification of data present in the messaging service message. The identification of the data and a message transmission history of the first user is used to enable selection of a message of a first entity. The selected message of the first entity is caused to be displayed by the communication application within a message framework that frames the first user messaging service message. The first entity message is caused to be included in the messaging service message transmitted to the second user device, wherein the first entity is not provided with access to the identity of the first user or the second user.

Abstract: A method for facilitating a remote conference includes receiving a digital video and a computer-readable audio signal. A face recognition machine is operated to recognize a face of a first conference participant in the digital video, and a speech recognition machine is operated to translate the computer-readable audio signal into a first text. An attribution machine attributes the text to the first conference participant. A second computer-readable audio signal is processed similarly, to obtain a second text attributed to a second conference participant. A transcription machine automatically creates a transcript including the first text attributed to the first conference participant and the second text attributed to the second conference participant.