Abstract: Methods and systems for optimization of interactive voice recognition (IVR) system processes are provided. One or more desired optimization parameters can be determined based on an IVR transaction log that includes a plurality of IVR journeys. The IVR journeys can be filtered, transformed into vectors and/or clustered.

Abstract: A system and method for acoustic echo cancellation is provided. Embodiments may include receiving, at one or more microphones, an audio reference signal from an audio speaker. Embodiments may also include filtering the audio reference signal using one or more adaptive audio filters. Embodiments may further include analyzing a level of signal energy of the audio reference signal with regard to time, frequency and audio channel to identify at least one maximum error contribution point. Embodiments may also include updating the one or more adaptive audio filters based upon, at least in part, the analyzed audio reference signal.

Abstract: A call may be received from a caller at an interactive voice response server with information indicating a caller preferred choice including a date and a time for an appointment. The caller preferred choice for the appointment may be determined as not available. A set of heuristic evaluations may be used to evaluate each of a plurality of available time slots individually to generate a plurality of intermediate results for each available time slot. Each intermediate result may have a weight associated with a corresponding heuristic evaluation. For each available time slot, the plurality of intermediate results may be aggregated using multiplicative weightings based on respective weights to produce aggregated results. A ranked list of candidate time slots to be used for the appointment may be generated based on the aggregated results and the caller may be prompted for a selection from the ranked list of candidate time slots.

Abstract: A method applied to a computer equipment, for providing a voice feedback information to a user in a call is provided in the present invention, wherein the method includes: acquiring a text information obtained by conducting a voice recognition on a voice information of the user; identifying a menu item to be jumped to, according to the text information in conjunction with a plurality of menu items of other party in the call, wherein the menu item to be jumped to is away from a present menu item by at least two levels; and jumping to the identified menu item, and sending the voice feedback information that corresponds to the menu item and is to be provided to the user. The present disclosure can achieve free conversion in the plurality of menu items of other party in the call.

Abstract: The disclosed computer-implemented method for detecting illegitimate voice calls may include (1) identifying an incoming voice call, (2) processing the incoming voice call in real time by (a) segmenting the incoming voice call into progressively produced call segments and, (b) for each new segment as the progressively produced call segments are produced, (A) extracting a set of features from the new segment and (B) feeding, as input into a neural network, the set of features and an output from the neural network generated based on a preceding segment of the incoming voice call, thereby generating a new output representing the current likelihood that the incoming voice call is illegitimate, (3) determining that the likelihood that the incoming voice call is illegitimate is above a predetermined threshold, and (4) performing a security action during the incoming voice call. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: A sound processing apparatus includes a detection unit adapted to detect a situation of a subject to be imaged from image data generated by imaging the subject to be imaged by an imaging unit; an extraction unit adapted to extract a feature amount of a sound from sound data generated by a sound acquisition unit corresponding to the imaging unit; and a determination unit adapted to execute a process of comparing the feature amount of the sound extracted by the extraction unit with a feature amount of a specific sound in accordance with the situation of the subject to be imaged detected by the detection unit, thereby determining whether the sound contains the specific sound.

Abstract: A sound output unit being detachably assembled to an electronic device is provided. The electronic device includes a housing and a connecting module disposed on the housing. The sound output unit includes a main body and a plug. The plug is electrically coupled to the main body. The plug is detachably assembled to the connecting module. The plug is adapted to rotate relative to connecting module along an axial line, such that a sensing component of the connecting module determines whether the sensing portion is sensed to make the electronic device switch between a first sound output mode and a second sound output mode. The plug has at least one conduction portion and a sensing portion on a circumferential surface of the plug, and the sensing portion is located on the at least one conduction portion.

Abstract: A noise and vibration sensing system is provided. The sensing system includes an acceleration sensor arrangement and a summer module. The acceleration sensor arrangement includes at least one acceleration sensor and is configured to generate at least two sense signals representative of acceleration that acts on the acceleration sensor arrangement. The at least two sense signals includes dynamic ranges that are ratios between maximum amplitudes of the at least two sense signals and noise created by the acceleration sensor arrangement. The summer module is configured to sum up the at least two sense signals to provide a sum signal that includes noise and a dynamic range which is a ratio between a maximum amplitude of the sum signal and the noise included in the sum signal. The dynamic range of the sum signal is greater than the arithmetic mean of the dynamic ranges of the at least two sense signals.

Abstract: A portable terminal, a hearing aid, and a method of indicating the position of a sound source in the portable terminal are provided. The method includes receiving sound signals of a plurality of sound sources, determining respective distances between the plurality of sound sources and the portable terminal, and respective directions of the plurality of sound sources from the portable terminal, based on the received sound signals of the plurality of sound sources, determining positions of the plurality of sound sources on the touch screen based on the determined distances and directions of the plurality of sound sources, and displaying the determined positions of the plurality of sound sources on the touch screen.

Abstract: Systems and methods are described relating to detection of audio of voice communications from different reference points containing an identical conversation or portion of a conversation. A method can use an analytics module operating on at least one processor. Call signatures of a plurality of audio of voice communications are received. An index loaded with the call signatures is created, where segments of the call signatures are associated with buckets of the index. A first subset of one or more of the buckets associated with a number of the segments that exceeds a threshold is identified. An identical conversation portion in two or more of the plurality of audio of voice communications is identified based on a second subset of one or more of the buckets, where the first subset of one or more of the buckets is disregarded.

Abstract: A method and apparatus for notifying an end user of a messaging event in a multi-user setting is disclosed. An apparatus that incorporates teachings of the present disclosure may include, for example, a non-transitory computer-readable storage medium in a communication device which includes computer instructions at least for matching a caller identifier associated with a messaging event and entries in a plurality of contact books corresponding to a plurality of users, and identifying a plurality of parties to whom the messaging event is potentially directed based on the matching. Additional embodiments are disclosed.

Abstract: Disclosed are various embodiments for detecting item scans with audio signal processing. A first machine-readable identifier may be rendered in a display device associated with at least one computing device, where the first machine-readable identifier is associated with a first item in a list of items. An audio signal may be captured using a microphone and analyzed to identify a predetermined tone in the audio signal indicative of a scan being performed on a register device. In response to the predetermined tone in the audio signal being identified, the first machine-readable identifier may be replaced with a second machine-readable identifier in the display device, where the second machine-readable identifier is associated with a second item in the list of items.

Abstract: A computer implemented method for communicating with contacts preferably responds to both telephone calls and written text documents, with calls being handled as they are received, and with written documents being temporarily stored before responding. Calls and written documents are monitored to determine the communication styles of the contacts and of the user in dealing with the contacts, with these styles then being applied to the responses, which include answers to questions from the contacts. Connections to other components and systems provide answers regarding the location and scheduling of the user, product inventories, etc.

Abstract: A surgical helmet assembly includes a surgical helmet, headphones mounted on the surgical helmet, and a noise cancellation system configured to supply a noise cancelling audio input to the headphones to mitigate unwanted ambient noise. A gain of the noise cancelling audio input is configurable to permit necessary feedback noise from surgical tools or the like to be heard by the wearer.

Abstract: An example implementation may involve driving an audio output module of a wearable device with a first audio signal and then receiving, via at least one microphone of wearable device, a second audio signal comprising first ambient noise. The device may determine that the first ambient noise is indicative of user speech and responsively duck the first audio signal. While the first audio signal is ducked, the device may detect, in a subsequent portion of the second audio signal, second ambient noise, and determine that the second ambient noise is indicative of ambient speech. Responsive to the determination that the second ambient noise is indicative of ambient speech, the device may continue the ducking of the first audio signal.

Abstract: Methods for generating an object based audio program which is renderable in a personalizable manner, e.g., to provide an immersive, perception of audio content of the program. Other embodiments include steps of delivering (e.g., broadcasting), decoding, and/or rendering such a program. Rendering of audio objects indicated by the program may provide an immersive experience. The audio content of the program may be indicative of multiple object channels (e.g., object channels indicative of user-selectable and user-configurable objects, and typically also a default set of objects which will be rendered in the absence of a selection by a user) and a bed of speaker channels. Another aspect is an audio processing unit (e.g., encoder or decoder) configured to perform, or which includes a buffer memory which stores at least one frame (or other segment) of an object based audio program (or bitstream thereof) generated in accordance with, any embodiment of the method.

Abstract: A method includes identifying, at a processor of a crosstalk analyzer, a first communication line of a plurality of communication lines and a second communication line of the plurality of communication lines. The first communication line and the second communication line identified based on a correlation of a crosstalk parameter with respect to the first communication line and the second communication line. The method also includes, responsive to identifying the first communication line and the second communication line, assigning, by the processor, the first communication line to a first port of an access node and the second communication line to a second port of the access node.

Abstract: Methods and systems directed to retrieving voicemails from a voice mailbox server. In particular embodiments, a mailbox server may receive a notification from the voice mailbox server and connect to the voice mailbox server providing the credentials of a client device, and pull new voicemails for storage at the mailbox server. In particular embodiments, mailbox server periodically polls voice mailbox server for new voicemail messages. In particular embodiments, a client device polls or receives notification of new voicemails, and transmits a downloaded message to the mailbox server.

Abstract: The present invention discloses a method for adjusting parameters of a sending device and a receiving device, and a terminal device. In the method, a new precoding parameter that needs to be used by a sending device on a line when a precoding matrix in a downlink direction of the line changes, and a new signal recovery parameter that needs to be used by a receiving device and matches the new precoding parameter are first acquired; and then the new precoding parameter, the new signal recovery parameter, and a set moment and/or symbol at which the sending device starts to use the new precoding parameter are sent to the sending device, and the new signal recovery parameter and the set moment and/or symbol are sent to the receiving device by using the sending device.

Abstract: The present system and method allow a customer service agent to preview an audio file of a customer's interaction with an interactive voice response (IVR) system before taking the call. While customer voice commands are typically used to navigate through an IVR system to reach an appropriate agent, the present system and method record the customer's voice commands in response to IVR prompts as an audio file and provide them to the agent before she or he takes the call. The agent may play the audio file on a customer engagement center desktop.