Abstract: Techniques are described for generating metric(s) that predict survey score(s) for a service session. Model(s) may be trained, through supervised or unsupervised machine learning, using training data such as communications from previous service sessions between service representative(s) and individual(s), and survey scores provided by the serviced individual to rate the session on one or more criteria (e.g., survey questions). The model(s) may be trained to output, based on an input session record, metric(s) that each correspond to a survey score that would have been provided by the individual had they completed the survey. The model may be a concatenated model that combines a language model output from a language classifier recurrent neural network, and an acoustic model output from an acoustic feature layer convolutional neural network. Individuals can be clustered according to the metric(s) and/or other factors, and the cluster(s) can be employed for routing incoming service requests.

Abstract: A micro-speaker, the manufacturing method thereof, a speaker device and an electronic apparatus are described herein. The micro-speaker comprises a case, wherein the case has an opening; and a piezoelectric layer, wherein one or more electrodes are provided on the piezoelectric layer, and wherein the piezoelectric layer is pre-buckled in its rest position, wherein the piezoelectric layer covers the opening and is bonded onto the case, to form a speaker rear cavity together with the case. The micro-speaker of the present invention has a relatively low speaker profile.

Abstract: A call challenger can receive a user input from a called party identity to opt-in to a call challenge service, and a second user input of a keyword. When the call challenger receives a call directed to a user equipment of the called party identity, the call challenger can prompt the calling party to provide an audible response. In response to a receipt of the audible response, the call challenger can convert the audible response to a text. The call challenger can compare the text with the keyword to determine if there is a sufficient match. In response to the determining the output of the comparing does not satisfy a threshold match score, the call challenger can prevent the call from connecting with the user equipment.

Abstract: Disclosed is a precision queuing (PQ) system that automatically and dynamically revises the values of precision queue step rules (PQSRs) with customizable thresholds based on current contact center conditions such as varying hours of operation and number of agents available.

Abstract: A schematic block diagram of an audio encoder for encoding a multichannel audio signal is shown. The audio encoder includes a linear prediction domain encoder, a frequency domain encoder, and a controller for switching between the linear prediction domain encoder and the frequency domain encoder. The controller is configured such that a portion of the multichannel signal is represented either by an encoded frame of the linear prediction domain encoder or by an encoded frame of the frequency domain encoder. The linear prediction domain encoder includes a downmixer for downmixing the multichannel signal to obtain a downmixed signal. The linear prediction domain encoder further includes a linear prediction domain core encoder for encoding the downmix signal and furthermore, the linear prediction domain encoder includes a first joint multichannel encoder for generating first multichannel information from the multichannel signal.

Abstract: A sound outputting device, a processing device and a sound controlling method thereof are provided. The sound controlling method includes the following steps. An original left sound signal and an original right sound signal are received. The original left sound signal and the original right sound signal are transformed to be a virtual left sound signal and a virtual right sound signal of a virtual sound source. A rotation degree of a user is detected. The virtual left sound signal and the virtual right sound signal are transformed to be an updated left sound signal and an updated right sound signal.

Abstract: A video stream of a video call between a communication endpoint of customer and a communication endpoint of a contact center agent is received. The video stream of the video call is processed in real-time to generate a real-time emotion transcript. The real-time emotion transcript tracks a plurality of separate emotions based on non-verbal expressions (e.g. facial expressions) that occur in the video stream of the video call. For example, different emotions of both the customer and the contact center agent may tracked in the real-time emotion transcript. The real-time emotion transcript is compared to an emotion transcript of at least one previous video call to determine if the video call should be handled differently in the contact center. In response to determining that video call should be handled differently in the contact center, an action determined to change how the video call is managed in the contact center.

Abstract: Various embodiments of the present technology comprise a method and apparatus for a microphone system. Various embodiments of the present technology may comprise a first microphone connected to a first high pass filter and a second microphone connected to a second high pass filter. The microphone system may further comprise a frequency controller configured to selectively activate the first high pass filter and the second high pass filter according to detected wind noise. The first and second high pass filters may be arranged to filter sound data from the first and second microphone prior to processing the sound data using beamforming.

Abstract: A dynamic communication management system manages the exchange of phone-based communications between devices using dynamically determined routing data. The routing for the phone-based communications can be dynamically determined such that certain identifying information is provided to destination devices instead of the identifying information that would be provided without the services of the dynamic communication management system.

Abstract: A contextual lead generation in an automated communication link establishment and management system may store information related to sales calls. The system may identify strengths and weaknesses of a sales representative. The system may provide training content to the sales representative in real time base on the identified strengths and weaknesses.

Abstract: Aspects describe a nozzle including a first flexible portion and a second rigid portion. The rigid portion is less flexible than the flexible portion. When positioned in a user's ear, the flexible portion extends a section of the earbud housing towards an ear canal of a user and the rigid portion couples a removable sealing structure to the earbud housing. In aspects, the flexible portion provides comfort by allowing a sealing structure to flex and accommodate a wearer's ear and the rigid portion provides structure for the feedback microphone to be placed close to the user's ear canal for ANR.

Abstract: A contact center system and related methods for handling teleservices in voice and data through a plurality of mobile devices such as smartphones is provided. The contact center system is characterized by a very wide functional platform for contact center fully integrated in a single system, with maximum elasticity to increase or decrease capacities based on the characteristics of the cloud, and capable to deliver via an agent mobile platform all the functionality of a fixed-up workstation into a smartphone. The contact center system according to the embodiments is capable to route a call from a customer's device, using a local telecommunications network, to the contact center system, which transforms it into a digital call; the call is assigned to an agent using a mobile platform.

Abstract: The present invention relates to a hearing device adapted to be positioned in an ear canal of a user, the hearing device comprising a receiver unit, a positioning member adapted to position and hold the hearing device in the ear canal of a user, and a vibration preventing arrangement adapted to prevent vibrations of a least part of the positioning member.

Abstract: In general, techniques are described by which to embed enhanced audio transports in backward compatible bitstreams. A device comprising a memory and one or more processors may be configured to perform the techniques. The memory may store the backward compatible bitstream, which conforms to a legacy transport format. The processor(s) may obtain, from the backward compatible bitstream, legacy audio data that conforms to a legacy audio format, and obtain, from the backward compatible bitstream, extended audio data that enhances the legacy audio data. The processor(s) may also obtain, based on the legacy audio data and the extended audio data, enhanced audio data that conforms to an enhanced audio format, and output the enhanced audio data to one or more speakers.

Abstract: A patient monitor can diagnose whether its speaker is blocked, malfunctioning, or at a volume that is too low. For example, the monitor can include a processor that can diagnose the speaker by recording a microphone input signal. The processor can compare the microphone input signal to an expected alarm signal that should be output by the speaker. If the two do not match or reasonably correspond to one another, then the processor may increase the volume of the alarm to determine whether doing so can overcome an obstruction, noise, or potential malfunction. The microphone can again detect the speaker output, and the processor can again make another comparison or analysis of the input with the speaker output. If the speaker output as detected via the microphone is still insufficiently loud, then the patient monitor may output an indication that the speaker has a problem.

Abstract: A determination is made that a real-time communication session (e.g., a voice call) between a first agent terminal and a customer communication endpoint has been placed on hold by a first contact center agent. An estimated hold time for the real-time communication is determined, based on a rule, in response to determining that the real-time communication session has been placed on hold. It is determined that the estimated hold time for the real-time communication session has expired. In response to determining that the estimated hold time for the real-time communication session has expired, one or more actions occur. For example, the real-time communication session is automatically transferred to a second agent terminal.

Abstract: Ambisonic audio is converted to binaural audio based on head related impulse responses (HRIRs) associated with sound sources located symmetric with respect to a head of a listener. The HRIRs associated with sound sources located symmetric with respect to the head of the listener are mapped to HRIR pairs associated with sound sources located on one side of the head of the listener based on the symmetry of the sound source locations. A sequence of HRIRs based on the mapped left HRIRs or a sequence of HRIRs based on the mapped right HRIRs are input into a spherical harmonics converter which outputs respective left spherical harmonics or right spherical harmonics. Ambisonic audio is binauralized based on the left spherical harmonics and the right spherical harmonics.

Abstract: A system that greatly improves contact center operations by converting inbound calls from communicating devices to outbound calls to the communicating devices. The system can include a call response agent that receives the inbound call from the communicating device, a speech-enabled automated agent that that interacts with the communicating device to receive an audio signal, a classifier that analyzes the audio signal and determines a caller request based on the audio signal, and a request package generator that creates an unallocated request package based on the caller request. The request package generator can create an unallocated request package menu, including the unallocated request package, and send the unallocated request package menu to a plurality of agent workstations.

Abstract: An apparatus configured, based on virtual reality content for viewing in virtual reality, the virtual reality content comprising visual content for display in a three dimensional virtual reality space and spatial audio content comprising audio for presentation such that it is audibly perceived to originate from one or more particular directions in the virtual reality space corresponding to one or more points or regions in the visual content, the virtual reality content defining at least a ground level of said virtual reality space; and based on display of a birds-eye view of the virtual reality space to a user comprising a view of the visual content substantially downward towards said ground level from a point of view location in said virtual reality space elevated from said ground level; to provide for presentation of said spatial audio content with a spatial audio modification, the spatial audio modification configured to modify the one or more particular directions from which the user perceives the spatial

Abstract: A mechanism is described for facilitating wind detection and wind noise reduction in computing environments according to one embodiment. An apparatus of embodiments, as described herein, includes wind detection logic to detect wind associated with the apparatus including a wearable computing device, wherein the wind is detected based on samples from multiple microphones and extraction and use of multiple features including spectral sub-band centroid (SSC) features and coherence features; and decision and execution logic to reduce wind noise associated with the detected wind.